dma kmalloc handling fixes

1. We need kmalloc_percpu for all of the now extended kmalloc caches
   array not just for each shift value.

2. init_kmem_cache_nodes() must assume node 0 locality for statically
   allocated dma kmem_cache structures even after boot is complete.
Reported-and-tested-by: NAlex Chiang <achiang@hp.com>
Signed-off-by: NChristoph Lameter <cl@linux-foundation.org>
Signed-off-by: NPekka Enberg <penberg@cs.helsinki.fi>

mm/slub.c

@@ -2062,7 +2062,7 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 #endif
 }
 
-static DEFINE_PER_CPU(struct kmem_cache_cpu, kmalloc_percpu[SLUB_PAGE_SHIFT]);
+static DEFINE_PER_CPU(struct kmem_cache_cpu, kmalloc_percpu[KMALLOC_CACHES]);
 
 static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
 {
@@ -2148,7 +2148,8 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 	int node;
 	int local_node;
 
-	if (slab_state >= UP)
+	if (slab_state >= UP && (s < kmalloc_caches ||
+			s > kmalloc_caches + KMALLOC_CACHES))
 		local_node = page_to_nid(virt_to_page(s));
 	else
 		local_node = 0;