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

[Chris Metcalf]

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.

-- 
Chris Metcalf, Tilera Corp.
http://www.tilera.com


--
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/