The patch titled Subject: exit: reparent: avoid find_new_reaper() if no children has been added to the -mm tree. Its filename is exit-reparent-avoid-find_new_reaper-if-no-children.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/exit-reparent-avoid-find_new_reaper-if-no-children.patch echo and later at echo http://ozlabs.org/~akpm/mmotm/broken-out/exit-reparent-avoid-find_new_reaper-if-no-children.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Oleg Nesterov <oleg@xxxxxxxxxx> Subject: exit: reparent: avoid find_new_reaper() if no children Now that pid_ns logic was isolated we can change forget_original_parent() to return right after find_child_reaper() when father->children is empty, there is nothing to reparent in this case. In particular this avoids find_alive_thread() and this can help if the whole process exits and it has a lot of PF_EXITING threads at the start of the thread list, this can easily lead to O(nr_threads ** 2) iterations. Trivial test case (tested under KVM, 2 CPUs): static void *tfunc(void *arg) { pause(); return NULL; } static int child(unsigned int nt) { pthread_t pt; while (nt--) assert(pthread_create(&pt, NULL, tfunc, NULL) == 0); pthread_kill(pt, SIGTRAP); pause(); return 0; } int main(int argc, const char *argv[]) { int stat; unsigned int nf = atoi(argv[1]); unsigned int nt = atoi(argv[2]); while (nf--) { if (!fork()) return child(nt); wait(&stat); assert(stat == SIGTRAP); } return 0; } $ time ./test 16 16536 shows: real user sys - 5m37.628s 0m4.437s 8m5.560s + 0m50.032s 0m7.130s 1m4.927s Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx> Cc: Aaron Tomlin <atomlin@xxxxxxxxxx> Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx> Cc: Sterling Alexander <stalexan@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- kernel/exit.c | 3 +++ 1 file changed, 3 insertions(+) diff -puN kernel/exit.c~exit-reparent-avoid-find_new_reaper-if-no-children kernel/exit.c --- a/kernel/exit.c~exit-reparent-avoid-find_new_reaper-if-no-children +++ a/kernel/exit.c @@ -571,6 +571,8 @@ static void forget_original_parent(struc /* Can drop and reacquire tasklist_lock */ reaper = find_child_reaper(father); + if (list_empty(&father->children)) + goto unlock; reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { @@ -591,6 +593,7 @@ static void forget_original_parent(struc reparent_leader(father, p, &dead_children); } list_splice_tail_init(&father->children, &reaper->children); + unlock: write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead_children, ptrace_entry) { _ Patches currently in -mm which might be from oleg@xxxxxxxxxx are mmfs-introduce-helpers-around-the-i_mmap_mutex.patch mm-use-new-helper-functions-around-the-i_mmap_mutex.patch mm-convert-i_mmap_mutex-to-rwsem.patch mm-rmap-share-the-i_mmap_rwsem.patch uprobes-share-the-i_mmap_rwsem.patch mm-xip-share-the-i_mmap_rwsem.patch mm-memory-failure-share-the-i_mmap_rwsem.patch mm-nommu-share-the-i_mmap_rwsem.patch mm-memoryc-share-the-i_mmap_rwsem.patch remove-unnecessary-is_valid_nodemask.patch proc-task_state-read-cred-group_info-outside-of-task_lock.patch proc-task_state-deuglify-the-max_fds-calculation.patch proc-task_state-move-the-main-seq_printf-outside-of-rcu_read_lock.patch proc-task_state-ptrace_parent-doesnt-need-pid_alive-check.patch sched_show_task-fix-unsafe-usage-of-real_parent.patch exit-reparent-use-ptrace_entry-rather-than-sibling-for-exit_dead-tasks.patch exit-reparent-cleanup-the-changing-of-parent.patch exit-reparent-cleanup-the-changing-of-parent-fix.patch exit-reparent-cleanup-the-usage-of-reparent_leader.patch exit-ptrace-shift-reap-dead-code-from-exit_ptrace-to-forget_original_parent.patch usermodehelper-dont-use-clone_vfork-for-____call_usermodehelper.patch usermodehelper-kill-the-kmod_thread_locker-logic.patch exit-wait-cleanup-the-ptrace_reparented-checks.patch exit-wait-cleanup-the-ptrace_reparented-checks-fix.patch exit-wait-dont-use-zombie-real_parent.patch exit-wait-drop-tasklist_lock-before-psig-c-accounting.patch exit-release_task-fix-the-comment-about-group-leader-accounting.patch exit-proc-dont-try-to-flush-proc-tgid-task-tgid.patch exit-reparent-fix-the-dead-parent-pr_set_child_subreaper-reparenting.patch exit-reparent-fix-the-cross-namespace-pr_set_child_subreaper-reparenting.patch exit-reparent-s-while_each_thread-for_each_thread-in-find_new_reaper.patch exit-reparent-document-the-has_child_subreaper-checks.patch exit-reparent-introduce-find_child_reaper.patch exit-reparent-introduce-find_alive_thread.patch exit-reparent-avoid-find_new_reaper-if-no-children.patch exit-reparent-call-forget_original_parent-under-tasklist_lock.patch exit-exit_notify-re-use-dead-list-to-autoreap-current.patch linux-next.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html