On 10/24/2012 12:56 PM, Pekka Enberg wrote:
> On Mon, Oct 22, 2012 at 5:05 PM, Glauber Costa <glommer@xxxxxxxxxxxxx> wrote:
>> +/**
>> + * kmem_cache_free - Deallocate an object
>> + * @cachep: The cache the allocation was from.
>> + * @objp: The previously allocated object.
>> + *
>> + * Free an object which was previously allocated from this
>> + * cache.
>> + */
>> +void kmem_cache_free(struct kmem_cache *s, void *x)
>> +{
>> + __kmem_cache_free(s, x);
>> + trace_kmem_cache_free(_RET_IP_, x);
>> +}
>> +EXPORT_SYMBOL(kmem_cache_free);
>
> As Christoph mentioned, this is going to hurt performance. The proper
> way to do this is to implement the *hook* in mm/slab_common.c and call
> that from all the allocator specific kmem_cache_free() functions.
>
> Pekka
>
We would ideally like the hooks to be inlined as well. Specially for the
memcg-disabled case, this will only get us a function call for no reason.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>