slab numa fallback logic: Do not pass unfiltered flags to page allocator

The NUMA fallback logic should be passing local_flags to kmem_get_pages() and not simply the
flags passed in.
Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Christoph Lameter <clameter@sgi.com>

mm/slab.c

@@ -3280,7 +3280,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 		if (local_flags & __GFP_WAIT)
 			local_irq_enable();
 		kmem_flagcheck(cache, flags);
-		obj = kmem_getpages(cache, flags, -1);
+		obj = kmem_getpages(cache, local_flags, -1);
 		if (local_flags & __GFP_WAIT)
 			local_irq_disable();
 		if (obj) {