1 files changed, 104 insertions, 154 deletions

diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 4ba34e95d835..3e16fe08150e 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -6,7 +6,6 @@
  *  Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
  */
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -23,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
+#include <linux/poison.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
@@ -41,8 +41,6 @@
 #include <asm/proto.h>
 #include <asm/smp.h>
 #include <asm/sections.h>
-#include <asm/dma-mapping.h>
-#include <asm/swiotlb.h>
 
 #ifndef Dprintk
 #define Dprintk(x...)
@@ -90,8 +88,6 @@ void show_mem(void)
 	printk(KERN_INFO "%lu pages swap cached\n",cached);
 }
 
-/* References to section boundaries */
-
 int after_bootmem;
 
 static __init void *spp_getpage(void)
@@ -233,7 +229,6 @@ __init void *early_ioremap(unsigned long addr, unsigned long size)
 
 	/* actually usually some more */
 	if (size >= LARGE_PAGE_SIZE) { 
-		printk("SMBIOS area too long %lu\n", size);
 		return NULL;
 	}
 	set_pmd(temp_mappings[0].pmd,  __pmd(map | _KERNPG_TABLE | _PAGE_PSE));
@@ -254,18 +249,24 @@ __init void early_iounmap(void *addr, unsigned long size)
 }
 
 static void __meminit
-phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end)
+phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
 {
-	int i;
+	int i = pmd_index(address);
 
-	for (i = 0; i < PTRS_PER_PMD; pmd++, i++, address += PMD_SIZE) {
+	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
 		unsigned long entry;
+		pmd_t *pmd = pmd_page + pmd_index(address);
 
-		if (address > end) {
-			for (; i < PTRS_PER_PMD; i++, pmd++)
-				set_pmd(pmd, __pmd(0));
+		if (address >= end) {
+			if (!after_bootmem)
+				for (; i < PTRS_PER_PMD; i++, pmd++)
+					set_pmd(pmd, __pmd(0));
 			break;
 		}
+
+		if (pmd_val(*pmd))
+			continue;
+
 		entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address;
 		entry &= __supported_pte_mask;
 		set_pmd(pmd, __pmd(entry));
@@ -275,45 +276,41 @@ phys_pmd_init(pmd_t *pmd, unsigned long address, unsigned long end)
 static void __meminit
 phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
 {
-	pmd_t *pmd = pmd_offset(pud, (unsigned long)__va(address));
-
-	if (pmd_none(*pmd)) {
-		spin_lock(&init_mm.page_table_lock);
-		phys_pmd_init(pmd, address, end);
-		spin_unlock(&init_mm.page_table_lock);
-		__flush_tlb_all();
-	}
+	pmd_t *pmd = pmd_offset(pud,0);
+	spin_lock(&init_mm.page_table_lock);
+	phys_pmd_init(pmd, address, end);
+	spin_unlock(&init_mm.page_table_lock);
+	__flush_tlb_all();
 }
 
-static void __meminit phys_pud_init(pud_t *pud, unsigned long address, unsigned long end)
+static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 { 
-	long i = pud_index(address);
+	int i = pud_index(addr);
 
-	pud = pud + i;
 
-	if (after_bootmem && pud_val(*pud)) {
-		phys_pmd_update(pud, address, end);
-		return;
-	}
-
-	for (; i < PTRS_PER_PUD; pud++, i++) {
+	for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) {
 		int map; 
-		unsigned long paddr, pmd_phys;
+		unsigned long pmd_phys;
+		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
 
-		paddr = (address & PGDIR_MASK) + i*PUD_SIZE;
-		if (paddr >= end)
+		if (addr >= end)
 			break;
 
-		if (!after_bootmem && !e820_any_mapped(paddr, paddr+PUD_SIZE, 0)) {
+		if (!after_bootmem && !e820_any_mapped(addr,addr+PUD_SIZE,0)) {
 			set_pud(pud, __pud(0)); 
 			continue;
 		} 
 
+		if (pud_val(*pud)) {
+			phys_pmd_update(pud, addr, end);
+			continue;
+		}
+
 		pmd = alloc_low_page(&map, &pmd_phys);
 		spin_lock(&init_mm.page_table_lock);
 		set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
-		phys_pmd_init(pmd, paddr, end);
+		phys_pmd_init(pmd, addr, end);
 		spin_unlock(&init_mm.page_table_lock);
 		unmap_low_page(map);
 	}
@@ -341,7 +338,8 @@ static void __init find_early_table_space(unsigned long end)
 	table_end = table_start;
 
 	early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, table_start << PAGE_SHIFT, table_end << PAGE_SHIFT);
+		end, table_start << PAGE_SHIFT,
+		(table_start << PAGE_SHIFT) + tables);
 }
 
 /* Setup the direct mapping of the physical memory at PAGE_OFFSET.
@@ -372,7 +370,7 @@ void __meminit init_memory_mapping(unsigned long start, unsigned long end)
 		pud_t *pud;
 
 		if (after_bootmem)
-			pud = pud_offset_k(pgd, start & PGDIR_MASK);
+			pud = pud_offset(pgd, start & PGDIR_MASK);
 		else
 			pud = alloc_low_page(&map, &pud_phys);
 
@@ -405,69 +403,15 @@ void __cpuinit zap_low_mappings(int cpu)
 	__flush_tlb_all();
 }
 
-/* Compute zone sizes for the DMA and DMA32 zones in a node. */
-__init void
-size_zones(unsigned long *z, unsigned long *h,
-	   unsigned long start_pfn, unsigned long end_pfn)
-{
- 	int i;
- 	unsigned long w;
-
- 	for (i = 0; i < MAX_NR_ZONES; i++)
- 		z[i] = 0;
-
- 	if (start_pfn < MAX_DMA_PFN)
- 		z[ZONE_DMA] = MAX_DMA_PFN - start_pfn;
- 	if (start_pfn < MAX_DMA32_PFN) {
- 		unsigned long dma32_pfn = MAX_DMA32_PFN;
- 		if (dma32_pfn > end_pfn)
- 			dma32_pfn = end_pfn;
- 		z[ZONE_DMA32] = dma32_pfn - start_pfn;
- 	}
- 	z[ZONE_NORMAL] = end_pfn - start_pfn;
-
- 	/* Remove lower zones from higher ones. */
- 	w = 0;
- 	for (i = 0; i < MAX_NR_ZONES; i++) {
- 		if (z[i])
- 			z[i] -= w;
- 	        w += z[i];
-	}
-
-	/* Compute holes */
-	w = start_pfn;
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		unsigned long s = w;
-		w += z[i];
-		h[i] = e820_hole_size(s, w);
-	}
-
-	/* Add the space pace needed for mem_map to the holes too. */
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE;
-
-	/* The 16MB DMA zone has the kernel and other misc mappings.
- 	   Account them too */
-	if (h[ZONE_DMA]) {
-		h[ZONE_DMA] += dma_reserve;
-		if (h[ZONE_DMA] >= z[ZONE_DMA]) {
-			printk(KERN_WARNING
-				"Kernel too large and filling up ZONE_DMA?\n");
-			h[ZONE_DMA] = z[ZONE_DMA];
-		}
-	}
-}
-
 #ifndef CONFIG_NUMA
 void __init paging_init(void)
 {
-	unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES];
-
+	unsigned long max_zone_pfns[MAX_NR_ZONES] = {MAX_DMA_PFN,
+							MAX_DMA32_PFN,
+							end_pfn};
 	memory_present(0, 0, end_pfn);
 	sparse_init();
-	size_zones(zones, holes, 0, end_pfn);
-	free_area_init_node(0, NODE_DATA(0), zones,
-			    __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
+	free_area_init_nodes(max_zone_pfns);
 }
 #endif
 
@@ -508,8 +452,6 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size)
 /*
  * Memory hotplug specific functions
  */
-#if defined(CONFIG_ACPI_HOTPLUG_MEMORY) || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)
-
 void online_page(struct page *page)
 {
 	ClearPageReserved(page);
@@ -519,31 +461,17 @@ void online_page(struct page *page)
 	num_physpages++;
 }
 
-#ifndef CONFIG_MEMORY_HOTPLUG
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
- * just online the pages.
+ * XXX: memory_add_physaddr_to_nid() is to find node id from physical address
+ *	via probe interface of sysfs. If acpi notifies hot-add event, then it
+ *	can tell node id by searching dsdt. But, probe interface doesn't have
+ *	node id. So, return 0 as node id at this time.
  */
-int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+#ifdef CONFIG_NUMA
+int memory_add_physaddr_to_nid(u64 start)
 {
-	int err = -EIO;
-	unsigned long pfn;
-	unsigned long total = 0, mem = 0;
-	for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
-		if (pfn_valid(pfn)) {
-			online_page(pfn_to_page(pfn));
-			err = 0;
-			mem++;
-		}
-		total++;
-	}
-	if (!err) {
-		z->spanned_pages += total;
-		z->present_pages += mem;
-		z->zone_pgdat->node_spanned_pages += total;
-		z->zone_pgdat->node_present_pages += mem;
-	}
-	return err;
+	return 0;
 }
 #endif
 
@@ -551,10 +479,10 @@ int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
-int add_memory(u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
 {
-	struct pglist_data *pgdat = NODE_DATA(0);
-	struct zone *zone = pgdat->node_zones + MAX_NR_ZONES-2;
+	struct pglist_data *pgdat = NODE_DATA(nid);
+	struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
@@ -570,7 +498,7 @@ error:
 	printk("%s: Problem encountered in __add_pages!\n", __func__);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(add_memory);
+EXPORT_SYMBOL_GPL(arch_add_memory);
 
 int remove_memory(u64 start, u64 size)
 {
@@ -578,7 +506,33 @@ int remove_memory(u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(remove_memory);
 
-#endif
+#else /* CONFIG_MEMORY_HOTPLUG */
+/*
+ * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
+ * just online the pages.
+ */
+int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+{
+	int err = -EIO;
+	unsigned long pfn;
+	unsigned long total = 0, mem = 0;
+	for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
+		if (pfn_valid(pfn)) {
+			online_page(pfn_to_page(pfn));
+			err = 0;
+			mem++;
+		}
+		total++;
+	}
+	if (!err) {
+		z->spanned_pages += total;
+		z->present_pages += mem;
+		z->zone_pgdat->node_spanned_pages += total;
+		z->zone_pgdat->node_present_pages += mem;
+	}
+	return err;
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
 			 kcore_vsyscall;
@@ -587,16 +541,7 @@ void __init mem_init(void)
 {
 	long codesize, reservedpages, datasize, initsize;
 
-#ifdef CONFIG_SWIOTLB
-	pci_swiotlb_init();
-#endif
-	no_iommu_init();
-
-	/* How many end-of-memory variables you have, grandma! */
-	max_low_pfn = end_pfn;
-	max_pfn = end_pfn;
-	num_physpages = end_pfn;
-	high_memory = (void *) __va(end_pfn * PAGE_SIZE);
+	pci_iommu_alloc();
 
 	/* clear the zero-page */
 	memset(empty_zero_page, 0, PAGE_SIZE);
@@ -609,7 +554,8 @@ void __init mem_init(void)
 #else
 	totalram_pages = free_all_bootmem();
 #endif
-	reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn);
+	reservedpages = end_pfn - totalram_pages -
+					absent_pages_in_range(0, end_pfn);
 
 	after_bootmem = 1;
 
@@ -644,34 +590,44 @@ void __init mem_init(void)
 #endif
 }
 
-void free_initmem(void)
+void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
 	unsigned long addr;
 
-	addr = (unsigned long)(&__init_begin);
-	for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
+	if (begin >= end)
+		return;
+
+	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
+	for (addr = begin; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE); 
+		memset((void *)(addr & ~(PAGE_SIZE-1)),
+			POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
-	memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
-	printk ("Freeing unused kernel memory: %luk freed\n", (__init_end - __init_begin) >> 10);
+}
+
+void free_initmem(void)
+{
+	memset(__initdata_begin, POISON_FREE_INITDATA,
+		__initdata_end - __initdata_begin);
+	free_init_pages("unused kernel memory",
+			(unsigned long)(&__init_begin),
+			(unsigned long)(&__init_end));
 }
 
 #ifdef CONFIG_DEBUG_RODATA
 
-extern char __start_rodata, __end_rodata;
 void mark_rodata_ro(void)
 {
-	unsigned long addr = (unsigned long)&__start_rodata;
+	unsigned long addr = (unsigned long)__start_rodata;
 
-	for (; addr < (unsigned long)&__end_rodata; addr += PAGE_SIZE)
+	for (; addr < (unsigned long)__end_rodata; addr += PAGE_SIZE)
 		change_page_attr_addr(addr, 1, PAGE_KERNEL_RO);
 
 	printk ("Write protecting the kernel read-only data: %luk\n",
-			(&__end_rodata - &__start_rodata) >> 10);
+			(__end_rodata - __start_rodata) >> 10);
 
 	/*
 	 * change_page_attr_addr() requires a global_flush_tlb() call after it.
@@ -686,15 +642,7 @@ void mark_rodata_ro(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (start >= end)
-		return;
-	printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
+	free_init_pages("initrd memory", start, end);
 }
 #endif
 
@@ -707,8 +655,10 @@ void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
 #else       		
 	reserve_bootmem(phys, len);    
 #endif
-	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE)
+	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
 		dma_reserve += len / PAGE_SIZE;
+		set_dma_reserve(dma_reserve);
+	}
 }
 
 int kern_addr_valid(unsigned long addr)