numa.c

			/*
			 * reserved region extends past the active region
			 *   get next active region that contains this
			 *   reserved region
			 */
			start_pfn = node_ar.end_pfn;
			physbase = start_pfn << PAGE_SHIFT;
			size = size - reserve_size;
			get_node_active_region(start_pfn, &node_ar);
		}
	}
}


void __init do_init_bootmem(void)
{
	int nid;

	min_low_pfn = 0;
	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
	max_pfn = max_low_pfn;

	if (parse_numa_properties())
		setup_nonnuma();
	else
		dump_numa_memory_topology();

	for_each_online_node(nid) {
		unsigned long start_pfn, end_pfn;
		void *bootmem_vaddr;
		unsigned long bootmap_pages;

		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);

		/*
		 * Allocate the node structure node local if possible
		 *
		 * Be careful moving this around, as it relies on all
		 * previous nodes' bootmem to be initialized and have
		 * all reserved areas marked.
		 */
		NODE_DATA(nid) = careful_zallocation(nid,
					sizeof(struct pglist_data),
					SMP_CACHE_BYTES, end_pfn);

  		dbg("node %d\n", nid);
		dbg("NODE_DATA() = %p\n", NODE_DATA(nid));

		NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
		NODE_DATA(nid)->node_start_pfn = start_pfn;
		NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;

		if (NODE_DATA(nid)->node_spanned_pages == 0)
  			continue;

  		dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT);
  		dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT);

		bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
		bootmem_vaddr = careful_zallocation(nid,
					bootmap_pages << PAGE_SHIFT,
					PAGE_SIZE, end_pfn);

		dbg("bootmap_vaddr = %p\n", bootmem_vaddr);

		init_bootmem_node(NODE_DATA(nid),
				  __pa(bootmem_vaddr) >> PAGE_SHIFT,
				  start_pfn, end_pfn);

		free_bootmem_with_active_regions(nid, end_pfn);
		/*
		 * Be very careful about moving this around.  Future
		 * calls to careful_zallocation() depend on this getting
		 * done correctly.
		 */
		mark_reserved_regions_for_nid(nid);
		sparse_memory_present_with_active_regions(nid);
	}

	init_bootmem_done = 1;

	/*
	 * Now bootmem is initialised we can create the node to cpumask
	 * lookup tables and setup the cpu callback to populate them.
	 */
	setup_node_to_cpumask_map();

	register_cpu_notifier(&ppc64_numa_nb);
	cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
			  (void *)(unsigned long)boot_cpuid);
}

void __init paging_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES];
	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
	max_zone_pfns[ZONE_DMA] = memblock_end_of_DRAM() >> PAGE_SHIFT;
	free_area_init_nodes(max_zone_pfns);
}

static int __init early_numa(char *p)
{
	if (!p)
		return 0;

	if (strstr(p, "off"))
		numa_enabled = 0;

	if (strstr(p, "debug"))
		numa_debug = 1;

	p = strstr(p, "fake=");
	if (p)
		cmdline = p + strlen("fake=");

	return 0;
}
early_param("numa", early_numa);

#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * Find the node associated with a hot added memory section for
 * memory represented in the device tree by the property
 * ibm,dynamic-reconfiguration-memory/ibm,dynamic-memory.
 */
static int hot_add_drconf_scn_to_nid(struct device_node *memory,
				     unsigned long scn_addr)
{
	const u32 *dm;
	unsigned int drconf_cell_cnt, rc;
	unsigned long lmb_size;
	struct assoc_arrays aa;
	int nid = -1;

	drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
	if (!drconf_cell_cnt)
		return -1;

	lmb_size = of_get_lmb_size(memory);
	if (!lmb_size)
		return -1;

	rc = of_get_assoc_arrays(memory, &aa);
	if (rc)
		return -1;

	for (; drconf_cell_cnt != 0; --drconf_cell_cnt) {
		struct of_drconf_cell drmem;

		read_drconf_cell(&drmem, &dm);

		/* skip this block if it is reserved or not assigned to
		 * this partition */
		if ((drmem.flags & DRCONF_MEM_RESERVED)
		    || !(drmem.flags & DRCONF_MEM_ASSIGNED))
			continue;

		if ((scn_addr < drmem.base_addr)
		    || (scn_addr >= (drmem.base_addr + lmb_size)))
			continue;

		nid = of_drconf_to_nid_single(&drmem, &aa);
		break;
	}

	return nid;
}

/*
 * Find the node associated with a hot added memory section for memory
 * represented in the device tree as a node (i.e. memory@XXXX) for
 * each memblock.
 */
int hot_add_node_scn_to_nid(unsigned long scn_addr)
{
	struct device_node *memory = NULL;
	int nid = -1;

	while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
		unsigned long start, size;
		int ranges;
		const unsigned int *memcell_buf;
		unsigned int len;

		memcell_buf = of_get_property(memory, "reg", &len);
		if (!memcell_buf || len <= 0)
			continue;

		/* ranges in cell */
		ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);

		while (ranges--) {
			start = read_n_cells(n_mem_addr_cells, &memcell_buf);
			size = read_n_cells(n_mem_size_cells, &memcell_buf);

			if ((scn_addr < start) || (scn_addr >= (start + size)))
				continue;

			nid = of_node_to_nid_single(memory);
			break;
		}

		of_node_put(memory);
		if (nid >= 0)
			break;
	}

	return nid;
}

/*
 * Find the node associated with a hot added memory section.  Section
 * corresponds to a SPARSEMEM section, not an MEMBLOCK.  It is assumed that
 * sections are fully contained within a single MEMBLOCK.
 */
int hot_add_scn_to_nid(unsigned long scn_addr)
{
	struct device_node *memory = NULL;
	int nid, found = 0;

	if (!numa_enabled || (min_common_depth < 0))
		return first_online_node;

	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
	if (memory) {
		nid = hot_add_drconf_scn_to_nid(memory, scn_addr);
		of_node_put(memory);
	} else {
		nid = hot_add_node_scn_to_nid(scn_addr);
	}

	if (nid < 0 || !node_online(nid))
		nid = first_online_node;

	if (NODE_DATA(nid)->node_spanned_pages)
		return nid;

	for_each_online_node(nid) {
		if (NODE_DATA(nid)->node_spanned_pages) {
			found = 1;
			break;
		}
	}

	BUG_ON(!found);
	return nid;
}

#endif /* CONFIG_MEMORY_HOTPLUG */