1 files changed, 77 insertions, 130 deletions
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index b6bcc9fa360..d497b6b0f5b 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -33,7 +33,6 @@
  */
 struct early_node_data {
 	struct ia64_node_data *node_data;
-	pg_data_t *pgdat;
 	unsigned long pernode_addr;
 	unsigned long pernode_size;
 	struct bootmem_data bootmem_data;
@@ -46,6 +45,8 @@ struct early_node_data {
 static struct early_node_data mem_data[MAX_NUMNODES] __initdata;
 static nodemask_t memory_less_mask __initdata;
 
+static pg_data_t *pgdat_list[MAX_NUMNODES];
+
 /*
  * To prevent cache aliasing effects, align per-node structures so that they
  * start at addresses that are strided by node number.
@@ -99,7 +100,7 @@ static int __init build_node_maps(unsigned long start, unsigned long len,
  * acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
  * called yet.  Note that node 0 will also count all non-existent cpus.
  */
-static int __init early_nr_cpus_node(int node)
+static int __meminit early_nr_cpus_node(int node)
 {
 	int cpu, n = 0;
 
@@ -114,7 +115,7 @@ static int __init early_nr_cpus_node(int node)
  * compute_pernodesize - compute size of pernode data
  * @node: the node id.
  */
-static unsigned long __init compute_pernodesize(int node)
+static unsigned long __meminit compute_pernodesize(int node)
 {
 	unsigned long pernodesize = 0, cpus;
 
@@ -175,13 +176,13 @@ static void __init fill_pernode(int node, unsigned long pernode,
 	pernode += PERCPU_PAGE_SIZE * cpus;
 	pernode += node * L1_CACHE_BYTES;
 
-	mem_data[node].pgdat = __va(pernode);
+	pgdat_list[node] = __va(pernode);
 	pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));
 
 	mem_data[node].node_data = __va(pernode);
 	pernode += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
 
-	mem_data[node].pgdat->bdata = bdp;
+	pgdat_list[node]->bdata = bdp;
 	pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));
 
 	cpu_data = per_cpu_node_setup(cpu_data, node);
@@ -268,7 +269,7 @@ static int __init find_pernode_space(unsigned long start, unsigned long len,
 static int __init free_node_bootmem(unsigned long start, unsigned long len,
 				    int node)
 {
-	free_bootmem_node(mem_data[node].pgdat, start, len);
+	free_bootmem_node(pgdat_list[node], start, len);
 
 	return 0;
 }
@@ -287,7 +288,7 @@ static void __init reserve_pernode_space(void)
 	int node;
 
 	for_each_online_node(node) {
-		pg_data_t *pdp = mem_data[node].pgdat;
+		pg_data_t *pdp = pgdat_list[node];
 
 		if (node_isset(node, memory_less_mask))
 			continue;
@@ -307,6 +308,27 @@ static void __init reserve_pernode_space(void)
 	}
 }
 
+static void __meminit scatter_node_data(void)
+{
+	pg_data_t **dst;
+	int node;
+
+	/*
+	 * for_each_online_node() can't be used at here.
+	 * node_online_map is not set for hot-added nodes at this time,
+	 * because we are halfway through initialization of the new node's
+	 * structures.  If for_each_online_node() is used, a new node's
+	 * pg_data_ptrs will be not initialized. Insted of using it,
+	 * pgdat_list[] is checked.
+	 */
+	for_each_node(node) {
+		if (pgdat_list[node]) {
+			dst = LOCAL_DATA_ADDR(pgdat_list[node])->pg_data_ptrs;
+			memcpy(dst, pgdat_list, sizeof(pgdat_list));
+		}
+	}
+}
+
 /**
  * initialize_pernode_data - fixup per-cpu & per-node pointers
  *
@@ -317,17 +339,10 @@ static void __init reserve_pernode_space(void)
  */
 static void __init initialize_pernode_data(void)
 {
-	pg_data_t *pgdat_list[MAX_NUMNODES];
 	int cpu, node;
 
-	for_each_online_node(node)
-		pgdat_list[node] = mem_data[node].pgdat;
+	scatter_node_data();
 
-	/* Copy the pg_data_t list to each node and init the node field */
-	for_each_online_node(node) {
-		memcpy(mem_data[node].node_data->pg_data_ptrs, pgdat_list,
-		       sizeof(pgdat_list));
-	}
 #ifdef CONFIG_SMP
 	/* Set the node_data pointer for each per-cpu struct */
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
@@ -372,7 +387,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
 	if (bestnode == -1)
 		bestnode = anynode;
 
-	ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat, pernodesize,
+	ptr = __alloc_bootmem_node(pgdat_list[bestnode], pernodesize,
 		PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
 
 	return ptr;
@@ -476,7 +491,7 @@ void __init find_memory(void)
 		pernodesize = mem_data[node].pernode_size;
 		map = pernode + pernodesize;
 
-		init_bootmem_node(mem_data[node].pgdat,
+		init_bootmem_node(pgdat_list[node],
 				  map>>PAGE_SHIFT,
 				  bdp->node_boot_start>>PAGE_SHIFT,
 				  bdp->node_low_pfn);
@@ -519,68 +534,6 @@ void __cpuinit *per_cpu_init(void)
 }
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_VIRTUAL_MEM_MAP
-static inline int find_next_valid_pfn_for_pgdat(pg_data_t *pgdat, int i)
-{
-	unsigned long end_address, hole_next_pfn;
-	unsigned long stop_address;
-
-	end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i];
-	end_address = PAGE_ALIGN(end_address);
-
-	stop_address = (unsigned long) &vmem_map[
-		pgdat->node_start_pfn + pgdat->node_spanned_pages];
-
-	do {
-		pgd_t *pgd;
-		pud_t *pud;
-		pmd_t *pmd;
-		pte_t *pte;
-
-		pgd = pgd_offset_k(end_address);
-		if (pgd_none(*pgd)) {
-			end_address += PGDIR_SIZE;
-			continue;
-		}
-
-		pud = pud_offset(pgd, end_address);
-		if (pud_none(*pud)) {
-			end_address += PUD_SIZE;
-			continue;
-		}
-
-		pmd = pmd_offset(pud, end_address);
-		if (pmd_none(*pmd)) {
-			end_address += PMD_SIZE;
-			continue;
-		}
-
-		pte = pte_offset_kernel(pmd, end_address);
-retry_pte:
-		if (pte_none(*pte)) {
-			end_address += PAGE_SIZE;
-			pte++;
-			if ((end_address < stop_address) &&
-			    (end_address != ALIGN(end_address, 1UL << PMD_SHIFT)))
-				goto retry_pte;
-			continue;
-		}
-		/* Found next valid vmem_map page */
-		break;
-	} while (end_address < stop_address);
-
-	end_address = min(end_address, stop_address);
-	end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1;
-	hole_next_pfn = end_address / sizeof(struct page);
-	return hole_next_pfn - pgdat->node_start_pfn;
-}
-#else
-static inline int find_next_valid_pfn_for_pgdat(pg_data_t *pgdat, int i)
-{
-	return i + 1;
-}
-#endif
-
 /**
  * show_mem - give short summary of memory stats
  *
@@ -594,15 +547,16 @@ void show_mem(void)
 	unsigned long total_present = 0;
 	pg_data_t *pgdat;
 
-	printk("Mem-info:\n");
+	printk(KERN_INFO "Mem-info:\n");
 	show_free_areas();
-	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
+	printk(KERN_INFO "Free swap:       %6ldkB\n",
+	       nr_swap_pages<<(PAGE_SHIFT-10));
+	printk(KERN_INFO "Node memory in pages:\n");
 	for_each_online_pgdat(pgdat) {
 		unsigned long present;
 		unsigned long flags;
 		int shared = 0, cached = 0, reserved = 0;
 
-		printk("Node ID: %d\n", pgdat->node_id);
 		pgdat_resize_lock(pgdat, &flags);
 		present = pgdat->node_present_pages;
 		for(i = 0; i < pgdat->node_spanned_pages; i++) {
@@ -610,7 +564,8 @@ void show_mem(void)
 			if (pfn_valid(pgdat->node_start_pfn + i))
 				page = pfn_to_page(pgdat->node_start_pfn + i);
 			else {
-				i = find_next_valid_pfn_for_pgdat(pgdat, i) - 1;
+				i = vmemmap_find_next_valid_pfn(pgdat->node_id,
+					 i) - 1;
 				continue;
 			}
 			if (PageReserved(page))
@@ -625,18 +580,17 @@ void show_mem(void)
 		total_reserved += reserved;
 		total_cached += cached;
 		total_shared += shared;
-		printk("\t%ld pages of RAM\n", present);
-		printk("\t%d reserved pages\n", reserved);
-		printk("\t%d pages shared\n", shared);
-		printk("\t%d pages swap cached\n", cached);
+		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
+		       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+		       present, reserved, shared, cached);
 	}
-	printk("%ld pages of RAM\n", total_present);
-	printk("%d reserved pages\n", total_reserved);
-	printk("%d pages shared\n", total_shared);
-	printk("%d pages swap cached\n", total_cached);
-	printk("Total of %ld pages in page table cache\n",
-		pgtable_quicklist_total_size());
-	printk("%d free buffer pages\n", nr_free_buffer_pages());
+	printk(KERN_INFO "%ld pages of RAM\n", total_present);
+	printk(KERN_INFO "%d reserved pages\n", total_reserved);
+	printk(KERN_INFO "%d pages shared\n", total_shared);
+	printk(KERN_INFO "%d pages swap cached\n", total_cached);
+	printk(KERN_INFO "Total of %ld pages in page table cache\n",
+	       pgtable_quicklist_total_size());
+	printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
 }
 
 /**
@@ -700,6 +654,7 @@ static __init int count_node_pages(unsigned long start, unsigned long len, int n
 {
 	unsigned long end = start + len;
 
+	add_active_range(node, start >> PAGE_SHIFT, end >> PAGE_SHIFT);
 	mem_data[node].num_physpages += len >> PAGE_SHIFT;
 	if (start <= __pa(MAX_DMA_ADDRESS))
 		mem_data[node].num_dma_physpages +=
@@ -724,10 +679,10 @@ static __init int count_node_pages(unsigned long start, unsigned long len, int n
 void __init paging_init(void)
 {
 	unsigned long max_dma;
-	unsigned long zones_size[MAX_NR_ZONES];
-	unsigned long zholes_size[MAX_NR_ZONES];
 	unsigned long pfn_offset = 0;
+	unsigned long max_pfn = 0;
 	int node;
+	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
 	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
@@ -736,53 +691,45 @@ void __init paging_init(void)
 	efi_memmap_walk(filter_rsvd_memory, count_node_pages);
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-	vmalloc_end -= PAGE_ALIGN(max_low_pfn * sizeof(struct page));
+	vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
+		sizeof(struct page));
 	vmem_map = (struct page *) vmalloc_end;
 	efi_memmap_walk(create_mem_map_page_table, NULL);
 	printk("Virtual mem_map starts at 0x%p\n", vmem_map);
 #endif
 
 	for_each_online_node(node) {
-		memset(zones_size, 0, sizeof(zones_size));
-		memset(zholes_size, 0, sizeof(zholes_size));
-
 		num_physpages += mem_data[node].num_physpages;
-
-		if (mem_data[node].min_pfn >= max_dma) {
-			/* All of this node's memory is above ZONE_DMA */
-			zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn;
-			zholes_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn -
-				mem_data[node].num_physpages;
-		} else if (mem_data[node].max_pfn < max_dma) {
-			/* All of this node's memory is in ZONE_DMA */
-			zones_size[ZONE_DMA] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn;
-			zholes_size[ZONE_DMA] = mem_data[node].max_pfn -
-				mem_data[node].min_pfn -
-				mem_data[node].num_dma_physpages;
-		} else {
-			/* This node has memory in both zones */
-			zones_size[ZONE_DMA] = max_dma -
-				mem_data[node].min_pfn;
-			zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] -
-				mem_data[node].num_dma_physpages;
-			zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
-				max_dma;
-			zholes_size[ZONE_NORMAL] = zones_size[ZONE_NORMAL] -
-				(mem_data[node].num_physpages -
-				 mem_data[node].num_dma_physpages);
-		}
-
 		pfn_offset = mem_data[node].min_pfn;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 		NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
 #endif
-		free_area_init_node(node, NODE_DATA(node), zones_size,
-				    pfn_offset, zholes_size);
+		if (mem_data[node].max_pfn > max_pfn)
+			max_pfn = mem_data[node].max_pfn;
 	}
 
+	max_zone_pfns[ZONE_DMA] = max_dma;
+	max_zone_pfns[ZONE_NORMAL] = max_pfn;
+	free_area_init_nodes(max_zone_pfns);
+
 	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
 }
+
+pg_data_t *arch_alloc_nodedata(int nid)
+{
+	unsigned long size = compute_pernodesize(nid);
+
+	return kzalloc(size, GFP_KERNEL);
+}
+
+void arch_free_nodedata(pg_data_t *pgdat)
+{
+	kfree(pgdat);
+}
+
+void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
+{
+	pgdat_list[update_node] = update_pgdat;
+	scatter_node_data();
+}