+#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
+ defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
+/* Only safe to use early in boot when initialisation is single-threaded */
+static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
+
+int __meminit early_pfn_to_nid(unsigned long pfn)
+{
+ int nid;
+
+ /* The system will behave unpredictably otherwise */
+ BUG_ON(system_state != SYSTEM_BOOTING);
+
+ nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
+ if (nid >= 0)
+ return nid;
+ /* just returns 0 */
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_NODES_SPAN_OTHER_NODES
+static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
+ struct mminit_pfnnid_cache *state)
+{
+ int nid;
+
+ nid = __early_pfn_to_nid(pfn, state);
+ if (nid >= 0 && nid != node)
+ return false;
+ return true;
+}
+
+/* Only safe to use early in boot when initialisation is single-threaded */
+static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+{
+ return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
+}
+
+#else
+
+static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+{
+ return true;
+}
+static inline bool __meminit meminit_pfn_in_nid(unsigned long pfn, int node,
+ struct mminit_pfnnid_cache *state)
+{
+ return true;
+}
+#endif
+
+
+void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
+ unsigned int order)
+{
+ if (early_page_uninitialised(pfn))
+ return;
+ return __free_pages_boot_core(page, pfn, order);
+}
+
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+static void __init deferred_free_range(struct page *page,
+ unsigned long pfn, int nr_pages)
+{
+ int i;
+
+ if (!page)
+ return;
+
+ /* Free a large naturally-aligned chunk if possible */
+ if (nr_pages == MAX_ORDER_NR_PAGES &&
+ (pfn & (MAX_ORDER_NR_PAGES-1)) == 0) {
+ set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ __free_pages_boot_core(page, pfn, MAX_ORDER-1);
+ return;
+ }
+
+ for (i = 0; i < nr_pages; i++, page++, pfn++)
+ __free_pages_boot_core(page, pfn, 0);
+}
+
+static __initdata DECLARE_RWSEM(pgdat_init_rwsem);
+
+/* Initialise remaining memory on a node */
+static int __init deferred_init_memmap(void *data)
+{
+ pg_data_t *pgdat = data;
+ int nid = pgdat->node_id;
+ struct mminit_pfnnid_cache nid_init_state = { };
+ unsigned long start = jiffies;
+ unsigned long nr_pages = 0;
+ unsigned long walk_start, walk_end;
+ int i, zid;
+ struct zone *zone;
+ unsigned long first_init_pfn = pgdat->first_deferred_pfn;
+ const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+
+ if (first_init_pfn == ULONG_MAX) {
+ up_read(&pgdat_init_rwsem);
+ return 0;
+ }
+
+ /* Bind memory initialisation thread to a local node if possible */
+ if (!cpumask_empty(cpumask))
+ set_cpus_allowed_ptr(current, cpumask);
+
+ /* Sanity check boundaries */
+ BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
+ BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
+ pgdat->first_deferred_pfn = ULONG_MAX;
+
+ /* Only the highest zone is deferred so find it */
+ for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ zone = pgdat->node_zones + zid;
+ if (first_init_pfn < zone_end_pfn(zone))
+ break;
+ }
+
+ for_each_mem_pfn_range(i, nid, &walk_start, &walk_end, NULL) {
+ unsigned long pfn, end_pfn;
+ struct page *page = NULL;
+ struct page *free_base_page = NULL;
+ unsigned long free_base_pfn = 0;
+ int nr_to_free = 0;
+
+ end_pfn = min(walk_end, zone_end_pfn(zone));
+ pfn = first_init_pfn;
+ if (pfn < walk_start)
+ pfn = walk_start;
+ if (pfn < zone->zone_start_pfn)
+ pfn = zone->zone_start_pfn;
+
+ for (; pfn < end_pfn; pfn++) {
+ if (!pfn_valid_within(pfn))
+ goto free_range;
+
+ /*
+ * Ensure pfn_valid is checked every
+ * MAX_ORDER_NR_PAGES for memory holes
+ */
+ if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
+ if (!pfn_valid(pfn)) {
+ page = NULL;
+ goto free_range;
+ }
+ }
+
+ if (!meminit_pfn_in_nid(pfn, nid, &nid_init_state)) {
+ page = NULL;
+ goto free_range;
+ }
+
+ /* Minimise pfn page lookups and scheduler checks */
+ if (page && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) {
+ page++;
+ } else {
+ nr_pages += nr_to_free;
+ deferred_free_range(free_base_page,
+ free_base_pfn, nr_to_free);
+ free_base_page = NULL;
+ free_base_pfn = nr_to_free = 0;
+
+ page = pfn_to_page(pfn);
+ cond_resched();
+ }
+
+ if (page->flags) {
+ VM_BUG_ON(page_zone(page) != zone);
+ goto free_range;
+ }
+
+ __init_single_page(page, pfn, zid, nid);
+ if (!free_base_page) {
+ free_base_page = page;
+ free_base_pfn = pfn;
+ nr_to_free = 0;
+ }
+ nr_to_free++;
+
+ /* Where possible, batch up pages for a single free */
+ continue;
+free_range:
+ /* Free the current block of pages to allocator */
+ nr_pages += nr_to_free;
+ deferred_free_range(free_base_page, free_base_pfn,
+ nr_to_free);
+ free_base_page = NULL;
+ free_base_pfn = nr_to_free = 0;
+ }
+
+ first_init_pfn = max(end_pfn, first_init_pfn);
+ }
+
+ /* Sanity check that the next zone really is unpopulated */
+ WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
+
+ pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
+ jiffies_to_msecs(jiffies - start));
+ up_read(&pgdat_init_rwsem);
+ return 0;
+}
+
+void __init page_alloc_init_late(void)
+{
+ int nid;
+
+ for_each_node_state(nid, N_MEMORY) {
+ down_read(&pgdat_init_rwsem);
+ kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
+ }
+
+ /* Block until all are initialised */
+ down_write(&pgdat_init_rwsem);
+ up_write(&pgdat_init_rwsem);
+}
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+