slab: shrink sizeof(struct kmem_cache)

Reduce high order allocations for some setups.
(NR_CPUS=4096 -> we need 64KB per kmem_cache struct)

We now allocate exact needed size (using nr_cpu_ids and nr_node_ids)

This also makes code a bit smaller on x86_64, since some field offsets
are less than the 127 limit :

Before patch :
# size mm/slab.o
   text    data     bss     dec     hex filename
  22605  361665      32  384302   5dd2e mm/slab.o

After patch :
# size mm/slab.o
   text    data     bss     dec     hex filename
  22349	 353473	   8224	 384046	  5dc2e	mm/slab.o

CC: Andrew Morton <akpm@linux-foundation.org>
Reported-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index d7f6311..d00e0ba 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -24,21 +24,19 @@
  */
 
 struct kmem_cache {
-/* 1) per-cpu data, touched during every alloc/free */
-	struct array_cache *array[NR_CPUS];
-/* 2) Cache tunables. Protected by cache_chain_mutex */
+/* 1) Cache tunables. Protected by cache_chain_mutex */
 	unsigned int batchcount;
 	unsigned int limit;
 	unsigned int shared;
 
 	unsigned int buffer_size;
 	u32 reciprocal_buffer_size;
-/* 3) touched by every alloc & free from the backend */
+/* 2) touched by every alloc & free from the backend */
 
 	unsigned int flags;		/* constant flags */
 	unsigned int num;		/* # of objs per slab */
 
-/* 4) cache_grow/shrink */
+/* 3) cache_grow/shrink */
 	/* order of pgs per slab (2^n) */
 	unsigned int gfporder;
 
@@ -54,11 +52,11 @@
 	/* constructor func */
 	void (*ctor)(void *obj);
 
-/* 5) cache creation/removal */
+/* 4) cache creation/removal */
 	const char *name;
 	struct list_head next;
 
-/* 6) statistics */
+/* 5) statistics */
 #ifdef CONFIG_DEBUG_SLAB
 	unsigned long num_active;
 	unsigned long num_allocations;
@@ -85,16 +83,18 @@
 	int obj_size;
 #endif /* CONFIG_DEBUG_SLAB */
 
+/* 6) per-cpu/per-node data, touched during every alloc/free */
 	/*
-	 * We put nodelists[] at the end of kmem_cache, because we want to size
-	 * this array to nr_node_ids slots instead of MAX_NUMNODES
+	 * We put array[] at the end of kmem_cache, because we want to size
+	 * this array to nr_cpu_ids slots instead of NR_CPUS
 	 * (see kmem_cache_init())
-	 * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
-	 * is statically defined, so we reserve the max number of nodes.
+	 * We still use [NR_CPUS] and not [1] or [0] because cache_cache
+	 * is statically defined, so we reserve the max number of cpus.
 	 */
-	struct kmem_list3 *nodelists[MAX_NUMNODES];
+	struct kmem_list3 **nodelists;
+	struct array_cache *array[NR_CPUS];
 	/*
-	 * Do not add fields after nodelists[]
+	 * Do not add fields after array[]
 	 */
 };