Re: [BUG] hackbench locks up with perf in 3.11-rc1 and beyond

[Steven Rostedt]

On Thu, 2013-08-08 at 14:04 +0900, Joonsoo Kim wrote:

> Sorry about it.
> Now, I think that this is a buggy commit, so should be reverted.
> 
> For confirm that, could I ask a question about your configuration, Steven?
> I guess, you may set 0 to all kmem caches's cpu_partial via sysfs, doesn't it?

Ah, you're right. As this box is also used to test the -rt patch,
there's a script installed to disable all cpu_partials. This is because
cpu_partials are known to cause non-deterministic behavior in -rt.

I forgot about that script, as this box is used for regular mainline
testing as well.

> 
> In this case, memory leak is possible in following case.
> Code flow of possible leak is follwing case.
> 
> * in __slab_free()
> 1. (!new.inuse || !prior) && !was_frozen
> 2. !kmem_cache_debug && !prior
> 3. new.frozen = 1
> 4. after cmpxchg_double_slab, run the (!n) case with new.frozen=1
> 5. with this patch, put_cpu_partial() doesn't do anything,
> 	because this cache's cpu_partial is 0
> 6. return
> 
> In step 5, leak occur.
> 
> I have a solution to prevent this problem, but in this stage, IMHO,
> reverting it may be better.

Yeah, I would suggest that too. As this seems to be a serious
regression.

Thanks!

-- Steve

--
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/