1 files changed, 168 insertions, 139 deletions

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index d497b6b0f5b..87862680536 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -16,11 +16,13 @@
 
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/nmi.h>
 #include <linux/swap.h>
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
 #include <linux/efi.h>
 #include <linux/nodemask.h>
+#include <linux/slab.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/meminit.h>
@@ -35,9 +37,9 @@ struct early_node_data {
 	struct ia64_node_data *node_data;
 	unsigned long pernode_addr;
 	unsigned long pernode_size;
-	struct bootmem_data bootmem_data;
-	unsigned long num_physpages;
+#ifdef CONFIG_ZONE_DMA
 	unsigned long num_dma_physpages;
+#endif
 	unsigned long min_pfn;
 	unsigned long max_pfn;
 };
@@ -45,7 +47,7 @@ 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];
+pg_data_t *pgdat_list[MAX_NUMNODES];
 
 /*
  * To prevent cache aliasing effects, align per-node structures so that they
@@ -72,23 +74,20 @@ static pg_data_t *pgdat_list[MAX_NUMNODES];
 static int __init build_node_maps(unsigned long start, unsigned long len,
 				  int node)
 {
-	unsigned long cstart, epfn, end = start + len;
-	struct bootmem_data *bdp = &mem_data[node].bootmem_data;
+	unsigned long spfn, epfn, end = start + len;
+	struct bootmem_data *bdp = &bootmem_node_data[node];
 
 	epfn = GRANULEROUNDUP(end) >> PAGE_SHIFT;
-	cstart = GRANULEROUNDDOWN(start);
+	spfn = GRANULEROUNDDOWN(start) >> PAGE_SHIFT;
 
 	if (!bdp->node_low_pfn) {
-		bdp->node_boot_start = cstart;
+		bdp->node_min_pfn = spfn;
 		bdp->node_low_pfn = epfn;
 	} else {
-		bdp->node_boot_start = min(cstart, bdp->node_boot_start);
+		bdp->node_min_pfn = min(spfn, bdp->node_min_pfn);
 		bdp->node_low_pfn = max(epfn, bdp->node_low_pfn);
 	}
 
-	min_low_pfn = min(min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT);
-	max_low_pfn = max(max_low_pfn, bdp->node_low_pfn);
-
 	return 0;
 }
 
@@ -104,7 +103,7 @@ static int __meminit early_nr_cpus_node(int node)
 {
 	int cpu, n = 0;
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++)
+	for_each_possible_early_cpu(cpu)
 		if (node == node_cpuid[cpu].nid)
 			n++;
 
@@ -124,6 +123,7 @@ static unsigned long __meminit compute_pernodesize(int node)
 	pernodesize += node * L1_CACHE_BYTES;
 	pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
 	pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
+	pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
 	pernodesize = PAGE_ALIGN(pernodesize);
 	return pernodesize;
 }
@@ -142,19 +142,121 @@ static void *per_cpu_node_setup(void *cpu_data, int node)
 #ifdef CONFIG_SMP
 	int cpu;
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++) {
-		if (node == node_cpuid[cpu].nid) {
-			memcpy(__va(cpu_data), __phys_per_cpu_start,
-			       __per_cpu_end - __per_cpu_start);
-			__per_cpu_offset[cpu] = (char*)__va(cpu_data) -
-				__per_cpu_start;
-			cpu_data += PERCPU_PAGE_SIZE;
-		}
+	for_each_possible_early_cpu(cpu) {
+		void *src = cpu == 0 ? __cpu0_per_cpu : __phys_per_cpu_start;
+
+		if (node != node_cpuid[cpu].nid)
+			continue;
+
+		memcpy(__va(cpu_data), src, __per_cpu_end - __per_cpu_start);
+		__per_cpu_offset[cpu] = (char *)__va(cpu_data) -
+			__per_cpu_start;
+
+		/*
+		 * percpu area for cpu0 is moved from the __init area
+		 * which is setup by head.S and used till this point.
+		 * Update ar.k3.  This move is ensures that percpu
+		 * area for cpu0 is on the correct node and its
+		 * virtual address isn't insanely far from other
+		 * percpu areas which is important for congruent
+		 * percpu allocator.
+		 */
+		if (cpu == 0)
+			ia64_set_kr(IA64_KR_PER_CPU_DATA,
+				    (unsigned long)cpu_data -
+				    (unsigned long)__per_cpu_start);
+
+		cpu_data += PERCPU_PAGE_SIZE;
 	}
 #endif
 	return cpu_data;
 }
 
+#ifdef CONFIG_SMP
+/**
+ * setup_per_cpu_areas - setup percpu areas
+ *
+ * Arch code has already allocated and initialized percpu areas.  All
+ * this function has to do is to teach the determined layout to the
+ * dynamic percpu allocator, which happens to be more complex than
+ * creating whole new ones using helpers.
+ */
+void __init setup_per_cpu_areas(void)
+{
+	struct pcpu_alloc_info *ai;
+	struct pcpu_group_info *uninitialized_var(gi);
+	unsigned int *cpu_map;
+	void *base;
+	unsigned long base_offset;
+	unsigned int cpu;
+	ssize_t static_size, reserved_size, dyn_size;
+	int node, prev_node, unit, nr_units, rc;
+
+	ai = pcpu_alloc_alloc_info(MAX_NUMNODES, nr_cpu_ids);
+	if (!ai)
+		panic("failed to allocate pcpu_alloc_info");
+	cpu_map = ai->groups[0].cpu_map;
+
+	/* determine base */
+	base = (void *)ULONG_MAX;
+	for_each_possible_cpu(cpu)
+		base = min(base,
+			   (void *)(__per_cpu_offset[cpu] + __per_cpu_start));
+	base_offset = (void *)__per_cpu_start - base;
+
+	/* build cpu_map, units are grouped by node */
+	unit = 0;
+	for_each_node(node)
+		for_each_possible_cpu(cpu)
+			if (node == node_cpuid[cpu].nid)
+				cpu_map[unit++] = cpu;
+	nr_units = unit;
+
+	/* set basic parameters */
+	static_size = __per_cpu_end - __per_cpu_start;
+	reserved_size = PERCPU_MODULE_RESERVE;
+	dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size;
+	if (dyn_size < 0)
+		panic("percpu area overflow static=%zd reserved=%zd\n",
+		      static_size, reserved_size);
+
+	ai->static_size		= static_size;
+	ai->reserved_size	= reserved_size;
+	ai->dyn_size		= dyn_size;
+	ai->unit_size		= PERCPU_PAGE_SIZE;
+	ai->atom_size		= PAGE_SIZE;
+	ai->alloc_size		= PERCPU_PAGE_SIZE;
+
+	/*
+	 * CPUs are put into groups according to node.  Walk cpu_map
+	 * and create new groups at node boundaries.
+	 */
+	prev_node = -1;
+	ai->nr_groups = 0;
+	for (unit = 0; unit < nr_units; unit++) {
+		cpu = cpu_map[unit];
+		node = node_cpuid[cpu].nid;
+
+		if (node == prev_node) {
+			gi->nr_units++;
+			continue;
+		}
+		prev_node = node;
+
+		gi = &ai->groups[ai->nr_groups++];
+		gi->nr_units		= 1;
+		gi->base_offset		= __per_cpu_offset[cpu] + base_offset;
+		gi->cpu_map		= &cpu_map[unit];
+	}
+
+	rc = pcpu_setup_first_chunk(ai, base);
+	if (rc)
+		panic("failed to setup percpu area (err=%d)", rc);
+
+	pcpu_free_alloc_info(ai);
+}
+#endif
+
 /**
  * fill_pernode - initialize pernode data.
  * @node: the node id.
@@ -166,7 +268,7 @@ static void __init fill_pernode(int node, unsigned long pernode,
 {
 	void *cpu_data;
 	int cpus = early_nr_cpus_node(node);
-	struct bootmem_data *bdp = &mem_data[node].bootmem_data;
+	struct bootmem_data *bdp = &bootmem_node_data[node];
 
 	mem_data[node].pernode_addr = pernode;
 	mem_data[node].pernode_size = pernodesize;
@@ -221,20 +323,21 @@ static void __init fill_pernode(int node, unsigned long pernode,
 static int __init find_pernode_space(unsigned long start, unsigned long len,
 				     int node)
 {
-	unsigned long epfn;
+	unsigned long spfn, epfn;
 	unsigned long pernodesize = 0, pernode, pages, mapsize;
-	struct bootmem_data *bdp = &mem_data[node].bootmem_data;
+	struct bootmem_data *bdp = &bootmem_node_data[node];
 
+	spfn = start >> PAGE_SHIFT;
 	epfn = (start + len) >> PAGE_SHIFT;
 
-	pages = bdp->node_low_pfn - (bdp->node_boot_start >> PAGE_SHIFT);
+	pages = bdp->node_low_pfn - bdp->node_min_pfn;
 	mapsize = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
 
 	/*
 	 * Make sure this memory falls within this node's usable memory
 	 * since we may have thrown some away in build_maps().
 	 */
-	if (start < bdp->node_boot_start || epfn > bdp->node_low_pfn)
+	if (spfn < bdp->node_min_pfn || epfn > bdp->node_low_pfn)
 		return 0;
 
 	/* Don't setup this node's local space twice... */
@@ -296,15 +399,15 @@ static void __init reserve_pernode_space(void)
 		bdp = pdp->bdata;
 
 		/* First the bootmem_map itself */
-		pages = bdp->node_low_pfn - (bdp->node_boot_start>>PAGE_SHIFT);
+		pages = bdp->node_low_pfn - bdp->node_min_pfn;
 		size = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
 		base = __pa(bdp->node_bootmem_map);
-		reserve_bootmem_node(pdp, base, size);
+		reserve_bootmem_node(pdp, base, size, BOOTMEM_DEFAULT);
 
 		/* Now the per-node space */
 		size = mem_data[node].pernode_size;
 		base = __pa(mem_data[node].pernode_addr);
-		reserve_bootmem_node(pdp, base, size);
+		reserve_bootmem_node(pdp, base, size, BOOTMEM_DEFAULT);
 	}
 }
 
@@ -318,7 +421,7 @@ static void __meminit scatter_node_data(void)
 	 * 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,
+	 * pg_data_ptrs will be not initialized. Instead of using it,
 	 * pgdat_list[] is checked.
 	 */
 	for_each_node(node) {
@@ -345,9 +448,10 @@ static void __init initialize_pernode_data(void)
 
 #ifdef CONFIG_SMP
 	/* Set the node_data pointer for each per-cpu struct */
-	for (cpu = 0; cpu < NR_CPUS; cpu++) {
+	for_each_possible_early_cpu(cpu) {
 		node = node_cpuid[cpu].nid;
-		per_cpu(cpu_info, cpu).node_data = mem_data[node].node_data;
+		per_cpu(ia64_cpu_info, cpu).node_data =
+			mem_data[node].node_data;
 	}
 #else
 	{
@@ -355,7 +459,7 @@ static void __init initialize_pernode_data(void)
 		cpu = 0;
 		node = node_cpuid[cpu].nid;
 		cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
-			((char *)&per_cpu__cpu_info - __per_cpu_start));
+			((char *)&ia64_cpu_info - __per_cpu_start));
 		cpu0_cpu_info->node_data = mem_data[node].node_data;
 	}
 #endif /* CONFIG_SMP */
@@ -412,37 +516,6 @@ static void __init memory_less_nodes(void)
 	return;
 }
 
-#ifdef CONFIG_SPARSEMEM
-/**
- * register_sparse_mem - notify SPARSEMEM that this memory range exists.
- * @start: physical start of range
- * @end: physical end of range
- * @arg: unused
- *
- * Simply calls SPARSEMEM to register memory section(s).
- */
-static int __init register_sparse_mem(unsigned long start, unsigned long end,
-	void *arg)
-{
-	int nid;
-
-	start = __pa(start) >> PAGE_SHIFT;
-	end = __pa(end) >> PAGE_SHIFT;
-	nid = early_pfn_to_nid(start);
-	memory_present(nid, start, end);
-
-	return 0;
-}
-
-static void __init arch_sparse_init(void)
-{
-	efi_memmap_walk(register_sparse_mem, NULL);
-	sparse_init();
-}
-#else
-#define arch_sparse_init() do {} while (0)
-#endif
-
 /**
  * find_memory - walk the EFI memory map and setup the bootmem allocator
  *
@@ -467,12 +540,16 @@ void __init find_memory(void)
 	/* These actually end up getting called by call_pernode_memory() */
 	efi_memmap_walk(filter_rsvd_memory, build_node_maps);
 	efi_memmap_walk(filter_rsvd_memory, find_pernode_space);
+	efi_memmap_walk(find_max_min_low_pfn, NULL);
 
 	for_each_online_node(node)
-		if (mem_data[node].bootmem_data.node_low_pfn) {
+		if (bootmem_node_data[node].node_low_pfn) {
 			node_clear(node, memory_less_mask);
 			mem_data[node].min_pfn = ~0UL;
 		}
+
+	efi_memmap_walk(filter_memory, register_active_ranges);
+
 	/*
 	 * Initialize the boot memory maps in reverse order since that's
 	 * what the bootmem allocator expects
@@ -486,14 +563,14 @@ void __init find_memory(void)
 		else if (node_isset(node, memory_less_mask))
 			continue;
 
-		bdp = &mem_data[node].bootmem_data;
+		bdp = &bootmem_node_data[node];
 		pernode = mem_data[node].pernode_addr;
 		pernodesize = mem_data[node].pernode_size;
 		map = pernode + pernodesize;
 
 		init_bootmem_node(pgdat_list[node],
 				  map>>PAGE_SHIFT,
-				  bdp->node_boot_start>>PAGE_SHIFT,
+				  bdp->node_min_pfn,
 				  bdp->node_low_pfn);
 	}
 
@@ -515,18 +592,14 @@ void __init find_memory(void)
  * find_pernode_space() does most of this already, we just need to set
  * local_per_cpu_offset
  */
-void __cpuinit *per_cpu_init(void)
+void *per_cpu_init(void)
 {
 	int cpu;
 	static int first_time = 1;
 
-
-	if (smp_processor_id() != 0)
-		return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
-
 	if (first_time) {
 		first_time = 0;
-		for (cpu = 0; cpu < NR_CPUS; cpu++)
+		for_each_possible_early_cpu(cpu)
 			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
 	}
 
@@ -535,65 +608,6 @@ void __cpuinit *per_cpu_init(void)
 #endif /* CONFIG_SMP */
 
 /**
- * show_mem - give short summary of memory stats
- *
- * Shows a simple page count of reserved and used pages in the system.
- * For discontig machines, it does this on a per-pgdat basis.
- */
-void show_mem(void)
-{
-	int i, total_reserved = 0;
-	int total_shared = 0, total_cached = 0;
-	unsigned long total_present = 0;
-	pg_data_t *pgdat;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
-	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;
-
-		pgdat_resize_lock(pgdat, &flags);
-		present = pgdat->node_present_pages;
-		for(i = 0; i < pgdat->node_spanned_pages; i++) {
-			struct page *page;
-			if (pfn_valid(pgdat->node_start_pfn + i))
-				page = pfn_to_page(pgdat->node_start_pfn + i);
-			else {
-				i = vmemmap_find_next_valid_pfn(pgdat->node_id,
-					 i) - 1;
-				continue;
-			}
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page)-1;
-		}
-		pgdat_resize_unlock(pgdat, &flags);
-		total_present += present;
-		total_reserved += reserved;
-		total_cached += cached;
-		total_shared += shared;
-		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-		       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
-		       present, reserved, shared, cached);
-	}
-	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());
-}
-
-/**
  * call_pernode_memory - use SRAT to call callback functions with node info
  * @start: physical start of range
  * @len: length of range
@@ -654,13 +668,12 @@ 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;
+#ifdef CONFIG_ZONE_DMA
 	if (start <= __pa(MAX_DMA_ADDRESS))
 		mem_data[node].num_dma_physpages +=
 			(min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
+#endif
 	start = GRANULEROUNDDOWN(start);
-	start = ORDERROUNDDOWN(start);
 	end = GRANULEROUNDUP(end);
 	mem_data[node].max_pfn = max(mem_data[node].max_pfn,
 				     end >> PAGE_SHIFT);
@@ -686,20 +699,20 @@ void __init paging_init(void)
 
 	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
-	arch_sparse_init();
-
 	efi_memmap_walk(filter_rsvd_memory, count_node_pages);
 
+	sparse_memory_present_with_active_regions(MAX_NUMNODES);
+	sparse_init();
+
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-	vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
+	VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
 		sizeof(struct page));
-	vmem_map = (struct page *) vmalloc_end;
+	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) {
-		num_physpages += mem_data[node].num_physpages;
 		pfn_offset = mem_data[node].min_pfn;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
@@ -709,13 +722,17 @@ void __init paging_init(void)
 			max_pfn = mem_data[node].max_pfn;
 	}
 
+	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA] = max_dma;
+#endif
 	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));
 }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
 pg_data_t *arch_alloc_nodedata(int nid)
 {
 	unsigned long size = compute_pernodesize(nid);
@@ -733,3 +750,15 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
 	pgdat_list[update_node] = update_pgdat;
 	scatter_node_data();
 }
+#endif
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
+{
+	return vmemmap_populate_basepages(start, end, node);
+}
+
+void vmemmap_free(unsigned long start, unsigned long end)
+{
+}
+#endif