Re: [rfc] SLOB memory ordering issue

[Nick Piggin]

On Thursday 16 October 2008 03:34, Nick Piggin wrote:
> I think I see a possible memory ordering problem with SLOB:
> In slab caches with constructors, the constructor is run
> before returning the object to caller, with no memory barrier
> afterwards.
>
> Now there is nothing that indicates the _exact_ behaviour
> required here. Is it at all reasonable to expect ->ctor() to
> be visible to all CPUs and not just the allocating CPU?
>
> SLAB and SLUB don't appear to have this problem. Of course,
> they have per-CPU fastpath queues, so _can_ have effectively
> exactly the same ordering issue if the object was brought
> back into the "initialized" state before being freed, rather
> than by ->ctor(). However in that case, it is at least
> kind of visible to the caller.

Although I guess it's just as much of a SLAB implementation
detail as the lack of ->ctor() barrier... And I really doubt
_any_ of the callers would have ever thought about either
possible problem.

I'd really hate to add a branch to the slab fastpath for this
though. Maybe we just have to document it, assume there are
no problems, and maybe take a look at some of the core users
of this.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/