powerpc/percpu: Update percpu bootmem allocator

This update the ppc64 version to be closer to x86/sparc.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200608070904.387440-1-aneesh.kumar@linux.ibm.com

arch/powerpc/kernel/setup_64.c

@@ -756,17 +756,46 @@ void __init emergency_stack_init(void)
 }
 
 #ifdef CONFIG_SMP
-#define PCPU_DYN_SIZE		()
-
-static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
+/**
+ * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
+ * @cpu: cpu to allocate for
+ * @size: size allocation in bytes
+ * @align: alignment
+ *
+ * Allocate @size bytes aligned at @align for cpu @cpu.  This wrapper
+ * does the right thing for NUMA regardless of the current
+ * configuration.
+ *
+ * RETURNS:
+ * Pointer to the allocated area on success, NULL on failure.
+ */
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size,
+					size_t align)
 {
-	return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS),
-				      MEMBLOCK_ALLOC_ACCESSIBLE,
-				      early_cpu_to_node(cpu));
+	const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	int node = early_cpu_to_node(cpu);
+	void *ptr;
 
+	if (!node_online(node) || !NODE_DATA(node)) {
+		ptr = memblock_alloc_from(size, align, goal);
+		pr_info("cpu %d has no node %d or node-local memory\n",
+			cpu, node);
+		pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
+			 cpu, size, __pa(ptr));
+	} else {
+		ptr = memblock_alloc_try_nid(size, align, goal,
+					     MEMBLOCK_ALLOC_ACCESSIBLE, node);
+		pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
+			 "%016lx\n", cpu, size, node, __pa(ptr));
+	}
+	return ptr;
+#else
+	return memblock_alloc_from(size, align, goal);
+#endif
 }
 
-static void __init pcpu_fc_free(void *ptr, size_t size)
+static void __init pcpu_free_bootmem(void *ptr, size_t size)
 {
 	memblock_free(__pa(ptr), size);
 }
@@ -801,7 +830,7 @@ void __init setup_per_cpu_areas(void)
 		atom_size = 1 << 20;
 
 	rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
-				    pcpu_fc_alloc, pcpu_fc_free);
+				    pcpu_alloc_bootmem, pcpu_free_bootmem);
 	if (rc < 0)
 		panic("cannot initialize percpu area (err=%d)", rc);