Re: [PATCH] slub: always align cpu_slab to honor cmpxchg_double requirement

From: Pekka Enberg
Date: Fri Jun 03 2011 - 01:57:35 EST

On Thu, Jun 2, 2011 at 9:13 PM, Chris Metcalf <cmetcalf@xxxxxxxxxx> wrote:
> On 6/2/2011 1:16 PM, David Rientjes wrote:
>> On Thu, 2 Jun 2011, Chris Metcalf wrote:
>>> On an architecture without CMPXCHG_LOCAL but with DEBUG_VM enabled,
>>> the VM_BUG_ON() in __pcpu_double_call_return_bool() will cause an early
>>> panic during boot unless we always align cpu_slab properly.
>>> In principle we could remove the alignment-testing VM_BUG_ON() for
>>> architectures that don't have CMPXCHG_LOCAL, but leaving it in means
>>> that new code will tend not to break x86 even if it is introduced
>>> on another platform, and it's low cost to require alignment.
>>> Signed-off-by: Chris Metcalf <cmetcalf@xxxxxxxxxx>
>> Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
>>> ---
>>> This needs to be pushed for 3.0 to allow arch/tile to boot.
>>> I'm happy to push it but I assume it would be better coming
>>> from an mm or percpu tree.  Thanks!
>> Should also be marked for stable for 2.6.39.x, right?
> No, in 2.6.39 the irqsafe_cpu_cmpxchg_double() was guarded under "#ifdef
> CONFIG_CMPXCHG_LOCAL".  Now it's not.  I suppose we could take the comment
> change in percpu.h for 2.6.39, but it probably doesn't merit churning the
> stable tree.

Yup. Looks good. Christoph?
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at