Pull sparsemem-v5 into release branch

arch/ia64/Kconfig

@@ -63,8 +63,6 @@ config IA64_GENERIC
 	select ACPI
 	select NUMA
 	select ACPI_NUMA
-	select VIRTUAL_MEM_MAP
-	select DISCONTIGMEM
 	help
 	  This selects the system type of your hardware.  A "generic" kernel
 	  will run on any supported IA-64 system.  However, if you configure
@@ -176,40 +174,6 @@ config IA64_L1_CACHE_SHIFT
 	default "6" if ITANIUM
 
 # align cache-sensitive data to 64 bytes
-config NUMA
-	bool "NUMA support"
-	depends on !IA64_HP_SIM
-	default y if IA64_SGI_SN2
-	select ACPI_NUMA
-	help
-	  Say Y to compile the kernel to support NUMA (Non-Uniform Memory
-	  Access).  This option is for configuring high-end multiprocessor
-	  server systems.  If in doubt, say N.
-
-config VIRTUAL_MEM_MAP
-	bool "Virtual mem map"
-	default y if !IA64_HP_SIM
-	help
-	  Say Y to compile the kernel with support for a virtual mem map.
-	  This code also only takes effect if a memory hole of greater than
-	  1 Gb is found during boot.  You must turn this option on if you
-	  require the DISCONTIGMEM option for your machine. If you are
-	  unsure, say Y.
-
-config HOLES_IN_ZONE
-	bool
-	default y if VIRTUAL_MEM_MAP
-
-config ARCH_DISCONTIGMEM_ENABLE
-	bool "Discontiguous memory support"
-	depends on (IA64_DIG || IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB) && NUMA && VIRTUAL_MEM_MAP
-	default y if (IA64_SGI_SN2 || IA64_GENERIC) && NUMA
-	help
-	  Say Y to support efficient handling of discontiguous physical memory,
-	  for architectures which are either NUMA (Non-Uniform Memory Access)
-	  or have huge holes in the physical address space for other reasons.
-	  See <file:Documentation/vm/numa> for more.
-
 config IA64_CYCLONE
 	bool "Cyclone (EXA) Time Source support"
 	help
@@ -232,8 +196,10 @@ config IA64_SGI_SN_XP
 	  based on a network adapter and DMA messaging.
 
 config FORCE_MAX_ZONEORDER
-	int
+	int "MAX_ORDER (11 - 17)"  if !HUGETLB_PAGE
-	default "18"
+	range 11 17  if !HUGETLB_PAGE
+	default "17" if HUGETLB_PAGE
+	default "11"
 
 config SMP
 	bool "Symmetric multi-processing support"
@@ -298,6 +264,58 @@ config PREEMPT
 
 source "mm/Kconfig"
 
+config ARCH_SELECT_MEMORY_MODEL
+	def_bool y
+
+config ARCH_DISCONTIGMEM_ENABLE
+	def_bool y
+	help
+	  Say Y to support efficient handling of discontiguous physical memory,
+	  for architectures which are either NUMA (Non-Uniform Memory Access)
+	  or have huge holes in the physical address space for other reasons.
+ 	  See <file:Documentation/vm/numa> for more.
+
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+
+config ARCH_SPARSEMEM_ENABLE
+	def_bool y
+	depends on ARCH_DISCONTIGMEM_ENABLE
+
+config ARCH_DISCONTIGMEM_DEFAULT
+	def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
+	depends on ARCH_DISCONTIGMEM_ENABLE
+
+config NUMA
+	bool "NUMA support"
+	depends on !IA64_HP_SIM && !FLATMEM
+	default y if IA64_SGI_SN2
+	help
+	  Say Y to compile the kernel to support NUMA (Non-Uniform Memory
+	  Access).  This option is for configuring high-end multiprocessor
+	  server systems.  If in doubt, say N.
+
+# VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
+# VIRTUAL_MEM_MAP has been retained for historical reasons.
+config VIRTUAL_MEM_MAP
+	bool "Virtual mem map"
+	depends on !SPARSEMEM
+	default y if !IA64_HP_SIM
+	help
+	  Say Y to compile the kernel with support for a virtual mem map.
+	  This code also only takes effect if a memory hole of greater than
+	  1 Gb is found during boot.  You must turn this option on if you
+	  require the DISCONTIGMEM option for your machine. If you are
+	  unsure, say Y.
+
+config HOLES_IN_ZONE
+	bool
+	default y if VIRTUAL_MEM_MAP
+
+config HAVE_ARCH_EARLY_PFN_TO_NID
+	def_bool y
+	depends on NEED_MULTIPLE_NODES
+
 config IA32_SUPPORT
 	bool "Support for Linux/x86 binaries"
 	help

arch/ia64/mm/Makefile

@@ -7,6 +7,5 @@ obj-y := init.o fault.o tlb.o extable.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
 obj-$(CONFIG_NUMA)	   += numa.o
 obj-$(CONFIG_DISCONTIGMEM) += discontig.o
-ifndef CONFIG_DISCONTIGMEM
+obj-$(CONFIG_SPARSEMEM)	   += discontig.o
-obj-y += contig.o
+obj-$(CONFIG_FLATMEM)	   += contig.o
-endif

arch/ia64/mm/contig.c

@@ -269,7 +269,7 @@ paging_init (void)
 	efi_memmap_walk(find_largest_hole, (u64 *)&max_gap);
 	if (max_gap < LARGE_GAP) {
 		vmem_map = (struct page *) 0;
-		free_area_init_node(0, &contig_page_data, zones_size, 0,
+		free_area_init_node(0, NODE_DATA(0), zones_size, 0,
 				    zholes_size);
 	} else {
 		unsigned long map_size;
@@ -282,7 +282,7 @@ paging_init (void)
 		efi_memmap_walk(create_mem_map_page_table, NULL);
 
 		NODE_DATA(0)->node_mem_map = vmem_map;
-		free_area_init_node(0, &contig_page_data, zones_size,
+		free_area_init_node(0, NODE_DATA(0), zones_size,
 				    0, zholes_size);
 
 		printk("Virtual mem_map starts at 0x%p\n", mem_map);

arch/ia64/mm/discontig.c

@@ -421,6 +421,37 @@ 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
  *
@@ -528,8 +559,10 @@ void show_mem(void)
 		int shared = 0, cached = 0, reserved = 0;
 		printk("Node ID: %d\n", pgdat->node_id);
 		for(i = 0; i < pgdat->node_spanned_pages; i++) {
-			struct page *page = pgdat_page_nr(pgdat, i);
+			struct page *page;
-			if (!ia64_pfn_valid(pgdat->node_start_pfn+i))
+			if (pfn_valid(pgdat->node_start_pfn + i))
+				page = pfn_to_page(pgdat->node_start_pfn + i);
+			else
 				continue;
 			if (PageReserved(page))
 				reserved++;
@@ -648,12 +681,16 @@ 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);
 
+#ifdef CONFIG_VIRTUAL_MEM_MAP
 	vmalloc_end -= PAGE_ALIGN(max_low_pfn * 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));
@@ -690,7 +727,9 @@ void __init paging_init(void)
 
 		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);
 	}

arch/ia64/mm/init.c

@@ -593,7 +593,7 @@ mem_init (void)
 	platform_dma_init();
 #endif
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_FLATMEM
 	if (!mem_map)
 		BUG();
 	max_mapnr = max_low_pfn;

arch/ia64/mm/numa.c

@@ -47,3 +47,27 @@ paddr_to_nid(unsigned long paddr)
 
 	return (i < num_node_memblks) ? node_memblk[i].nid : (num_node_memblks ? -1 : 0);
 }
+
+#if defined(CONFIG_SPARSEMEM) && defined(CONFIG_NUMA)
+/*
+ * Because of holes evaluate on section limits.
+ * If the section of memory exists, then return the node where the section
+ * resides.  Otherwise return node 0 as the default.  This is used by
+ * SPARSEMEM to allocate the SPARSEMEM sectionmap on the NUMA node where
+ * the section resides.
+ */
+int early_pfn_to_nid(unsigned long pfn)
+{
+	int i, section = pfn >> PFN_SECTION_SHIFT, ssec, esec;
+
+	for (i = 0; i < num_node_memblks; i++) {
+		ssec = node_memblk[i].start_paddr >> PA_SECTION_SHIFT;
+		esec = (node_memblk[i].start_paddr + node_memblk[i].size +
+			((1L << PA_SECTION_SHIFT) - 1)) >> PA_SECTION_SHIFT;
+		if (section >= ssec && section < esec)
+			return node_memblk[i].nid;
+	}
+
+	return 0;
+}
+#endif

include/asm-ia64/meminit.h

@@ -43,7 +43,7 @@ extern void efi_memmap_init(unsigned long *, unsigned long *);
 #define GRANULEROUNDUP(n)	(((n)+IA64_GRANULE_SIZE-1) & ~(IA64_GRANULE_SIZE-1))
 #define ORDERROUNDDOWN(n)	((n) & ~((PAGE_SIZE<<MAX_ORDER)-1))
 
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
   extern void call_pernode_memory (unsigned long start, unsigned long len, void *func);
 #else
 # define call_pernode_memory(start, len, func)	(*func)(start, len, 0)

include/asm-ia64/mmzone.h

@@ -15,7 +15,7 @@
 #include <asm/page.h>
 #include <asm/meminit.h>
 
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
 
 static inline int pfn_to_nid(unsigned long pfn)
 {
@@ -31,6 +31,10 @@ static inline int pfn_to_nid(unsigned long pfn)
 #endif
 }
 
+#ifdef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+extern int early_pfn_to_nid(unsigned long pfn);
+#endif
+
 #ifdef CONFIG_IA64_DIG /* DIG systems are small */
 # define MAX_PHYSNODE_ID	8
 # define NR_NODE_MEMBLKS	(MAX_NUMNODES * 8)
@@ -39,8 +43,8 @@ static inline int pfn_to_nid(unsigned long pfn)
 # define NR_NODE_MEMBLKS	(MAX_NUMNODES * 4)
 #endif
 
-#else /* CONFIG_DISCONTIGMEM */
+#else /* CONFIG_NUMA */
 # define NR_NODE_MEMBLKS	(MAX_NUMNODES * 4)
-#endif /* CONFIG_DISCONTIGMEM */
+#endif /* CONFIG_NUMA */
 
 #endif /* _ASM_IA64_MMZONE_H */

include/asm-ia64/nodedata.h

@@ -17,7 +17,7 @@
 #include <asm/percpu.h>
 #include <asm/mmzone.h>
 
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NUMA
 
 /*
  * Node Data. One of these structures is located on each node of a NUMA system.
@@ -47,6 +47,6 @@ struct ia64_node_data {
  */
 #define NODE_DATA(nid)		(local_node_data->pg_data_ptrs[nid])
 
-#endif /* CONFIG_DISCONTIGMEM */
+#endif /* CONFIG_NUMA */
 
 #endif /* _ASM_IA64_NODEDATA_H */

include/asm-ia64/page.h

@@ -102,15 +102,15 @@ do {						\
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 extern int ia64_pfn_valid (unsigned long pfn);
-#else
+#elif defined(CONFIG_FLATMEM)
 # define ia64_pfn_valid(pfn) 1
 #endif
 
-#ifndef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_FLATMEM
 # define pfn_valid(pfn)		(((pfn) < max_mapnr) && ia64_pfn_valid(pfn))
 # define page_to_pfn(page)	((unsigned long) (page - mem_map))
 # define pfn_to_page(pfn)	(mem_map + (pfn))
-#else
+#elif defined(CONFIG_DISCONTIGMEM)
 extern struct page *vmem_map;
 extern unsigned long max_low_pfn;
 # define pfn_valid(pfn)		(((pfn) < max_low_pfn) && ia64_pfn_valid(pfn))

include/asm-ia64/sparsemem.h

@@ -0,0 +1,20 @@
+#ifndef _ASM_IA64_SPARSEMEM_H
+#define _ASM_IA64_SPARSEMEM_H
+
+#ifdef CONFIG_SPARSEMEM
+/*
+ * SECTION_SIZE_BITS            2^N: how big each section will be
+ * MAX_PHYSMEM_BITS             2^N: how much memory we can have in that space
+ */
+
+#define SECTION_SIZE_BITS	(30)
+#define MAX_PHYSMEM_BITS	(50)
+#ifdef CONFIG_FORCE_MAX_ZONEORDER
+#if ((CONFIG_FORCE_MAX_ZONEORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS)
+#undef SECTION_SIZE_BITS
+#define SECTION_SIZE_BITS (CONFIG_FORCE_MAX_ZONEORDER - 1 + PAGE_SHIFT)
+#endif
+#endif
+
+#endif /* CONFIG_SPARSEMEM */
+#endif /* _ASM_IA64_SPARSEMEM_H */