On 10/19/2012 06:25 PM, Christoph Lameter wrote:
> The nodelists field in kmem_cache is pointing to the first unused
> object in the array field when bootstrap is complete.
>
> A problem with the current approach is that the statically sized
> kmem_cache structure use on boot can only contain NR_CPUS entries.
> If the number of nodes plus the number of cpus is greater then we
> would overwrite memory following the kmem_cache_boot definition.
>
> Increase the size of the array field to ensure that also the node
> pointers fit into the array field.
>
> Once we do that we no longer need the kmem_cache_nodelists
> array and we can then also use that structure elsewhere.
Fair.
One comment:
> /*
> + * The memory after the last cpu cache pointer is used for the
> + * the nodelists pointer.
> + */
> +static void setup_nodelists_pointer(struct kmem_cache *s)
> +{
> + s->nodelists = (struct kmem_list3 **)&s->array[nr_cpu_ids];
> +}
> +
> +/*
> * Initialisation. Called after the page allocator have been initialised and
> * before smp_init().
> */
> @@ -1590,13 +1597,15 @@ void __init kmem_cache_init(void)
> int node;
>
> kmem_cache = &kmem_cache_boot;
> + setup_nodelists_pointer(kmem_cache);
>
> if (num_possible_nodes() == 1)
> use_alien_caches = 0;
>
> +
> for (i = 0; i < NUM_INIT_LISTS; i++) {
> kmem_list3_init(&initkmem_list3[i]);
> - if (i < MAX_NUMNODES)
> + if (i < nr_node_ids)
> kmem_cache->nodelists[i] = NULL;
> }
With nodelists being part of kmem_cache, and kmem_cache being allocated
with kmem_cache_zalloc, it seems to me that you can actually just get
rid of the inner loop instead of patching it. But this is orthogonal to
this patch...
So:
Acked-by: Glauber Costa <glommer@xxxxxxxxxxxxx>
--
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>