quoted

quoted

We shouldn't really rely on mmap_sem for this IMO.

  Yes, We should rely on mmap_sem for vma->vm_policy,but not for
  process context policy(task->mempolicy).

But the caller has no way to know which kind of policy is returned so
the locking cannot be conditional on the policy type.

Yes. vma->vm_policy is protected by mmap_sem, which is reliable if
we want to add a new apis(pidfd_mbind()) to change the vma->vm_policy
specified in pidfd. but not for pidfd_set_mempolicy(task->mempolicy is
protected by alloc_lock).

Yes this is all understood but the level of the overhead is not really
clear. So the question is whether this will induce a visible overhead.

OK,i will try it.

Because from the maintainability point of view it is much less costly to
have a clear life time model. Right now we have a mix of reference
counting and per-task requirements which is rather subtle and easy to
get wrong. In an ideal world we would have get_vma_policy always
returning a reference counted policy or NULL. If we really need to
optimize for cache line bouncing we can go with per cpu reference
counters (something that was not available at the time the mempolicy
code has been introduced).

So I am not saying that the task_work based solution is not possible I
just think that this looks like a good opportunity to get from the
existing subtle model.

OK, i got it. Thanks for your reply and suggestions.


Zhongkun.