numa.c

linux-2.6.15.6

	 * We use lmb_end_of_DRAM() in here instead of memory_limit because
	 * we've already adjusted it for the limit and it takes care of
	 * having memory holes below the limit.
	 */

	if (! memory_limit)
		return size;

	if (start + size <= lmb_end_of_DRAM())
		return size;

	if (start >= lmb_end_of_DRAM())
		return 0;

	return lmb_end_of_DRAM() - start;
}

static int __init parse_numa_properties(void)
{
	struct device_node *cpu = NULL;
	struct device_node *memory = NULL;
	int addr_cells, size_cells;
	int max_domain;
	unsigned long i;

	if (numa_enabled == 0) {
		printk(KERN_WARNING "NUMA disabled by user\n");
		return -1;
	}

	min_common_depth = find_min_common_depth();

	dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth);
	if (min_common_depth < 0)
		return min_common_depth;

	max_domain = numa_setup_cpu(boot_cpuid);

	/*
	 * Even though we connect cpus to numa domains later in SMP init,
	 * we need to know the maximum node id now. This is because each
	 * node id must have NODE_DATA etc backing it.
	 * As a result of hotplug we could still have cpus appear later on
	 * with larger node ids. In that case we force the cpu into node 0.
	 */
	for_each_cpu(i) {
		int numa_domain;

		cpu = find_cpu_node(i);

		if (cpu) {
			numa_domain = of_node_numa_domain(cpu);
			of_node_put(cpu);

			if (numa_domain < MAX_NUMNODES &&
			    max_domain < numa_domain)
				max_domain = numa_domain;
		}
	}

	addr_cells = get_mem_addr_cells();
	size_cells = get_mem_size_cells();
	memory = NULL;
	while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
		unsigned long start;
		unsigned long size;
		int numa_domain;
		int ranges;
		unsigned int *memcell_buf;
		unsigned int len;

		memcell_buf = (unsigned int *)get_property(memory, "reg", &len);
		if (!memcell_buf || len <= 0)
			continue;

		ranges = memory->n_addrs;
new_range:
		/* these are order-sensitive, and modify the buffer pointer */
		start = read_n_cells(addr_cells, &memcell_buf);
		size = read_n_cells(size_cells, &memcell_buf);

		numa_domain = of_node_numa_domain(memory);

		if (numa_domain >= MAX_NUMNODES) {
			if (numa_domain != 0xffff)
				printk(KERN_ERR "WARNING: memory at %lx maps "
				       "to invalid NUMA node %d\n", start,
				       numa_domain);
			numa_domain = 0;
		}

		if (max_domain < numa_domain)
			max_domain = numa_domain;

		if (!(size = numa_enforce_memory_limit(start, size))) {
			if (--ranges)
				goto new_range;
			else
				continue;
		}

		add_region(numa_domain, start >> PAGE_SHIFT,
			   size >> PAGE_SHIFT);

		if (--ranges)
			goto new_range;
	}

	for (i = 0; i <= max_domain; i++)
		node_set_online(i);

	return 0;
}

static void __init setup_nonnuma(void)
{
	unsigned long top_of_ram = lmb_end_of_DRAM();
	unsigned long total_ram = lmb_phys_mem_size();
	unsigned int i;

	printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
	       top_of_ram, total_ram);
	printk(KERN_INFO "Memory hole size: %ldMB\n",
	       (top_of_ram - total_ram) >> 20);

	map_cpu_to_node(boot_cpuid, 0);
	for (i = 0; i < lmb.memory.cnt; ++i)
		add_region(0, lmb.memory.region[i].base >> PAGE_SHIFT,
			   lmb_size_pages(&lmb.memory, i));
	node_set_online(0);
}

static void __init dump_numa_topology(void)
{
	unsigned int node;
	unsigned int count;

	if (min_common_depth == -1 || !numa_enabled)
		return;

	for_each_online_node(node) {
		unsigned long i;

		printk(KERN_INFO "Node %d Memory:", node);

		count = 0;

		for (i = 0; i < lmb_end_of_DRAM();
		     i += (1 << SECTION_SIZE_BITS)) {
			if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) {
				if (count == 0)
					printk(" 0x%lx", i);
				++count;
			} else {
				if (count > 0)
					printk("-0x%lx", i);
				count = 0;
			}
		}

		if (count > 0)
			printk("-0x%lx", i);
		printk("\n");
	}
	return;
}

/*
 * Allocate some memory, satisfying the lmb or bootmem allocator where
 * required. nid is the preferred node and end is the physical address of
 * the highest address in the node.
 *
 * Returns the physical address of the memory.
 */
static void __init *careful_allocation(int nid, unsigned long size,
				       unsigned long align,
				       unsigned long end_pfn)
{
	int new_nid;
	unsigned long ret = lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT);

	/* retry over all memory */
	if (!ret)
		ret = lmb_alloc_base(size, align, lmb_end_of_DRAM());

	if (!ret)
		panic("numa.c: cannot allocate %lu bytes on node %d",
		      size, nid);

	/*
	 * If the memory came from a previously allocated node, we must
	 * retry with the bootmem allocator.
	 */
	new_nid = early_pfn_to_nid(ret >> PAGE_SHIFT);
	if (new_nid < nid) {
		ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(new_nid),
				size, align, 0);

		if (!ret)
			panic("numa.c: cannot allocate %lu bytes on node %d",
			      size, new_nid);

		ret = __pa(ret);

		dbg("alloc_bootmem %lx %lx\n", ret, size);
	}

	return (void *)ret;
}

void __init do_init_bootmem(void)
{
	int nid;
	unsigned int i;
	static struct notifier_block ppc64_numa_nb = {
		.notifier_call = cpu_numa_callback,
		.priority = 1 /* Must run before sched domains notifier. */
	};

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

	if (parse_numa_properties())
		setup_nonnuma();
	else
		dump_numa_topology();

	register_cpu_notifier(&ppc64_numa_nb);

	for_each_online_node(nid) {
		unsigned long start_pfn, end_pfn, pages_present;
		unsigned long bootmem_paddr;
		unsigned long bootmap_pages;

		get_region(nid, &start_pfn, &end_pfn, &pages_present);

		/* Allocate the node structure node local if possible */
		NODE_DATA(nid) = careful_allocation(nid,
					sizeof(struct pglist_data),
					SMP_CACHE_BYTES, end_pfn);
		NODE_DATA(nid) = __va(NODE_DATA(nid));
		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));

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

		NODE_DATA(nid)->bdata = &plat_node_bdata[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_paddr = (unsigned long)careful_allocation(nid,
					bootmap_pages << PAGE_SHIFT,
					PAGE_SIZE, end_pfn);
		memset(__va(bootmem_paddr), 0, bootmap_pages << PAGE_SHIFT);

		dbg("bootmap_paddr = %lx\n", bootmem_paddr);

		init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
				  start_pfn, end_pfn);

		/* Add free regions on this node */
		for (i = 0; init_node_data[i].end_pfn; i++) {
			unsigned long start, end;

			if (init_node_data[i].nid != nid)
				continue;

			start = init_node_data[i].start_pfn << PAGE_SHIFT;
			end = init_node_data[i].end_pfn << PAGE_SHIFT;

			dbg("free_bootmem %lx %lx\n", start, end - start);
  			free_bootmem_node(NODE_DATA(nid), start, end - start);
		}

		/* Mark reserved regions on this node */
		for (i = 0; i < lmb.reserved.cnt; i++) {
			unsigned long physbase = lmb.reserved.region[i].base;
			unsigned long size = lmb.reserved.region[i].size;
			unsigned long start_paddr = start_pfn << PAGE_SHIFT;
			unsigned long end_paddr = end_pfn << PAGE_SHIFT;

			if (early_pfn_to_nid(physbase >> PAGE_SHIFT) != nid &&
			    early_pfn_to_nid((physbase+size-1) >> PAGE_SHIFT) != nid)
				continue;

			if (physbase < end_paddr &&
			    (physbase+size) > start_paddr) {
				/* overlaps */
				if (physbase < start_paddr) {
					size -= start_paddr - physbase;
					physbase = start_paddr;
				}

				if (size > end_paddr - physbase)
					size = end_paddr - physbase;

				dbg("reserve_bootmem %lx %lx\n", physbase,
				    size);
				reserve_bootmem_node(NODE_DATA(nid), physbase,
						     size);
			}
		}

		/* Add regions into sparsemem */
		for (i = 0; init_node_data[i].end_pfn; i++) {
			unsigned long start, end;

			if (init_node_data[i].nid != nid)
				continue;

			start = init_node_data[i].start_pfn;
			end = init_node_data[i].end_pfn;

			memory_present(nid, start, end);
		}
	}
}

void __init paging_init(void)
{
	unsigned long zones_size[MAX_NR_ZONES];
	unsigned long zholes_size[MAX_NR_ZONES];
	int nid;

	memset(zones_size, 0, sizeof(zones_size));
	memset(zholes_size, 0, sizeof(zholes_size));

	for_each_online_node(nid) {
		unsigned long start_pfn, end_pfn, pages_present;

		get_region(nid, &start_pfn, &end_pfn, &pages_present);

		zones_size[ZONE_DMA] = end_pfn - start_pfn;
		zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - pages_present;

		dbg("free_area_init node %d %lx %lx (hole: %lx)\n", nid,
		    zones_size[ZONE_DMA], start_pfn, zholes_size[ZONE_DMA]);

		free_area_init_node(nid, NODE_DATA(nid), zones_size, start_pfn,
				    zholes_size);
	}
}

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;

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