On 08/19, Suren Baghdasaryan wrote:
>
> Since the combination of CLONE_VM and !CLONE_SIGHAND is rarely
> used the additional mutex lock in that path of the clone() syscall should
> not affect its overall performance. Clearing the MMF_PROC_SHARED flag
> (when the last process sharing the mm exits) is left out of this patch to
> keep it simple and because it is believed that this threading model is
> rare.
vfork() ?
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1403,6 +1403,15 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
> if (clone_flags & CLONE_VM) {
> mmget(oldmm);
> mm = oldmm;
> + if (!(clone_flags & CLONE_SIGHAND)) {
I agree with Christian, you need CLONE_THREAD
> + /* We need to synchronize with __set_oom_adj */
> + mutex_lock(&oom_adj_lock);
> + set_bit(MMF_PROC_SHARED, &mm->flags);
> + /* Update the values in case they were changed after copy_signal */
> + tsk->signal->oom_score_adj = current->signal->oom_score_adj;
> + tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min;
> + mutex_unlock(&oom_adj_lock);
I don't understand how this can close the race with __set_oom_adj...
What if __set_oom_adj() is called right after mutex_unlock() ? It will see
MMF_PROC_SHARED, but for_each_process() won't find the new child until
copy_process() does list_add_tail_rcu(&p->tasks, &init_task.tasks) ?
Oleg.
