X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=arch%2Fx86%2Fmm%2Finit_32.c;h=262867a7d43855348c0e1e661a034822fd1c4dc6;hb=9b3be9f99203d9a400e8547f0e80f1d8f8e5738c;hp=9b5f7d7049d044c78f017f1f33377ac5db4caed7;hpb=a2699e477b8e6b17d4da64916f766dd5a2576c9c;p=safe%2Fjmp%2Flinux-2.6

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 9b5f7d7..262867a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
@@ -31,6 +32,7 @@
 #include <linux/cpumask.h>
 
 #include <asm/asm.h>
+#include <asm/bios_ebda.h>
 #include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -47,35 +49,25 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
+#include <asm/page_types.h>
+#include <asm/init.h>
 
-unsigned int __VMALLOC_RESERVE = 128 << 20;
-
-unsigned long max_low_pfn_mapped;
-unsigned long max_pfn_mapped;
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 unsigned long highstart_pfn, highend_pfn;
 
 static noinline int do_test_wp_bit(void);
 
+bool __read_mostly __vmalloc_start_set = false;
 
-static unsigned long __initdata table_start;
-static unsigned long __meminitdata table_end;
-static unsigned long __meminitdata table_top;
-
-static int __initdata after_init_bootmem;
-
-static __init void *alloc_low_page(unsigned long *phys)
+static __init void *alloc_low_page(void)
 {
-	unsigned long pfn = table_end++;
+	unsigned long pfn = e820_table_end++;
 	void *adr;
 
-	if (pfn >= table_top)
+	if (pfn >= e820_table_top)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = __va(pfn * PAGE_SIZE);
 	memset(adr, 0, PAGE_SIZE);
-	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
 
@@ -90,16 +82,17 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 	pmd_t *pmd_table;
 
 #ifdef CONFIG_X86_PAE
-	unsigned long phys;
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
-		if (after_init_bootmem)
-			pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+		if (after_bootmem)
+			pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE);
 		else
-			pmd_table = (pmd_t *)alloc_low_page(&phys);
+			pmd_table = (pmd_t *)alloc_low_page();
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 		pud = pud_offset(pgd, 0);
 		BUG_ON(pmd_table != pmd_offset(pud, 0));
+
+		return pmd_table;
 	}
 #endif
 	pud = pud_offset(pgd, 0);
@@ -117,17 +110,15 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
 		pte_t *page_table = NULL;
 
-		if (after_init_bootmem) {
-#ifdef CONFIG_DEBUG_PAGEALLOC
+		if (after_bootmem) {
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
 			page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
 #endif
 			if (!page_table)
 				page_table =
-				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
-		} else {
-			unsigned long phys;
-			page_table = (pte_t *)alloc_low_page(&phys);
-		}
+				(pte_t *)alloc_bootmem_pages(PAGE_SIZE);
+		} else
+			page_table = (pte_t *)alloc_low_page();
 
 		paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
@@ -137,6 +128,64 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	return pte_offset_kernel(pmd, 0);
 }
 
+pmd_t * __init populate_extra_pmd(unsigned long vaddr)
+{
+	int pgd_idx = pgd_index(vaddr);
+	int pmd_idx = pmd_index(vaddr);
+
+	return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx;
+}
+
+pte_t * __init populate_extra_pte(unsigned long vaddr)
+{
+	int pte_idx = pte_index(vaddr);
+	pmd_t *pmd;
+
+	pmd = populate_extra_pmd(vaddr);
+	return one_page_table_init(pmd) + pte_idx;
+}
+
+static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
+					   unsigned long vaddr, pte_t *lastpte)
+{
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * Something (early fixmap) may already have put a pte
+	 * page here, which causes the page table allocation
+	 * to become nonlinear. Attempt to fix it, and if it
+	 * is still nonlinear then we have to bug.
+	 */
+	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+
+	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
+	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
+	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
+	    && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start
+		|| (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) {
+		pte_t *newpte;
+		int i;
+
+		BUG_ON(after_bootmem);
+		newpte = alloc_low_page();
+		for (i = 0; i < PTRS_PER_PTE; i++)
+			set_pte(newpte + i, pte[i]);
+
+		paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
+		set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
+		BUG_ON(newpte != pte_offset_kernel(pmd, 0));
+		__flush_tlb_all();
+
+		paravirt_release_pte(__pa(pte) >> PAGE_SHIFT);
+		pte = newpte;
+	}
+	BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1)
+	       && vaddr > fix_to_virt(FIX_KMAP_END)
+	       && lastpte && lastpte + PTRS_PER_PTE != pte);
+#endif
+	return pte;
+}
+
 /*
  * This function initializes a certain range of kernel virtual memory
  * with new bootmem page tables, everywhere page tables are missing in
@@ -153,6 +202,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 	unsigned long vaddr;
 	pgd_t *pgd;
 	pmd_t *pmd;
+	pte_t *pte = NULL;
 
 	vaddr = start;
 	pgd_idx = pgd_index(vaddr);
@@ -164,7 +214,8 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 		pmd = pmd + pmd_index(vaddr);
 		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
 							pmd++, pmd_idx++) {
-			one_page_table_init(pmd);
+			pte = page_table_kmap_check(one_page_table_init(pmd),
+			                            pmd, vaddr, pte);
 
 			vaddr += PMD_SIZE;
 		}
@@ -184,11 +235,14 @@ static inline int is_kernel_text(unsigned long addr)
  * of max_low_pfn pages, by creating page tables starting from address
  * PAGE_OFFSET:
  */
-static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
-						unsigned long start_pfn,
-						unsigned long end_pfn,
-						int use_pse)
+unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+			     unsigned long end,
+			     unsigned long page_size_mask)
 {
+	int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+	unsigned long start_pfn, end_pfn;
+	pgd_t *pgd_base = swapper_pg_dir;
 	int pgd_idx, pmd_idx, pte_ofs;
 	unsigned long pfn;
 	pgd_t *pgd;
@@ -197,6 +251,9 @@ static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
 	unsigned pages_2m, pages_4k;
 	int mapping_iter;
 
+	start_pfn = start >> PAGE_SHIFT;
+	end_pfn = end >> PAGE_SHIFT;
+
 	/*
 	 * First iteration will setup identity mapping using large/small pages
 	 * based on use_pse, with other attributes same as set by
@@ -311,28 +368,9 @@ repeat:
 		mapping_iter = 2;
 		goto repeat;
 	}
-}
-
-/*
- * devmem_is_allowed() checks to see if /dev/mem access to a certain address
- * is valid. The argument is a physical page number.
- *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains bios code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
- */
-int devmem_is_allowed(unsigned long pagenr)
-{
-	if (pagenr <= 256)
-		return 1;
-	if (!page_is_ram(pagenr))
-		return 1;
 	return 0;
 }
 
-#ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
 pgprot_t kmap_prot;
 
@@ -355,6 +393,7 @@ static void __init kmap_init(void)
 	kmap_prot = PAGE_KERNEL;
 }
 
+#ifdef CONFIG_HIGHMEM
 static void __init permanent_kmaps_init(pgd_t *pgd_base)
 {
 	unsigned long vaddr;
@@ -373,7 +412,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
 	pkmap_page_table = pte;
 }
 
-static void __init add_one_highpage_init(struct page *page, int pfn)
+static void __init add_one_highpage_init(struct page *page)
 {
 	ClearPageReserved(page);
 	init_page_count(page);
@@ -406,7 +445,7 @@ static int __init add_highpages_work_fn(unsigned long start_pfn,
 		if (!pfn_valid(node_pfn))
 			continue;
 		page = pfn_to_page(node_pfn);
-		add_one_highpage_init(page, node_pfn);
+		add_one_highpage_init(page);
 	}
 
 	return 0;
@@ -424,19 +463,10 @@ void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
 	work_with_active_regions(nid, add_highpages_work_fn, &data);
 }
 
-#ifndef CONFIG_NUMA
-static void __init set_highmem_pages_init(void)
+#else
+static inline void permanent_kmaps_init(pgd_t *pgd_base)
 {
-	add_highpages_with_active_regions(0, highstart_pfn, highend_pfn);
-
-	totalram_pages += totalhigh_pages;
 }
-#endif /* !CONFIG_NUMA */
-
-#else
-# define kmap_init()				do { } while (0)
-# define permanent_kmaps_init(pgd_base)		do { } while (0)
-# define set_highmem_pages_init()	do { } while (0)
 #endif /* CONFIG_HIGHMEM */
 
 void __init native_pagetable_setup_start(pgd_t *base)
@@ -494,15 +524,15 @@ void __init native_pagetable_setup_done(pgd_t *base)
  * be partially populated, and so it avoids stomping on any existing
  * mappings.
  */
-static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base)
+void __init early_ioremap_page_table_range_init(void)
 {
+	pgd_t *pgd_base = swapper_pg_dir;
 	unsigned long vaddr, end;
 
 	/*
 	 * Fixed mappings, only the page table structure has to be
 	 * created - mappings will be set by set_fixmap():
 	 */
-	early_ioremap_clear();
 	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
 	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
 	page_table_range_init(vaddr, end, pgd_base);
@@ -513,11 +543,7 @@ static void __init pagetable_init(void)
 {
 	pgd_t *pgd_base = swapper_pg_dir;
 
-	paravirt_pagetable_setup_start(pgd_base);
-
 	permanent_kmaps_init(pgd_base);
-
-	paravirt_pagetable_setup_done(pgd_base);
 }
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -538,7 +564,7 @@ static inline void save_pg_dir(void)
 }
 #endif /* !CONFIG_ACPI_SLEEP */
 
-void zap_low_mappings(void)
+void zap_low_mappings(bool early)
 {
 	int i;
 
@@ -555,63 +581,15 @@ void zap_low_mappings(void)
 		set_pgd(swapper_pg_dir+i, __pgd(0));
 #endif
 	}
-	flush_tlb_all();
-}
-
-int nx_enabled;
-
-pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL);
-EXPORT_SYMBOL_GPL(__supported_pte_mask);
-
-#ifdef CONFIG_X86_PAE
-
-static int disable_nx __initdata;
-
-/*
- * noexec = on|off
- *
- * Control non executable mappings.
- *
- * on      Enable
- * off     Disable
- */
-static int __init noexec_setup(char *str)
-{
-	if (!str || !strcmp(str, "on")) {
-		if (cpu_has_nx) {
-			__supported_pte_mask |= _PAGE_NX;
-			disable_nx = 0;
-		}
-	} else {
-		if (!strcmp(str, "off")) {
-			disable_nx = 1;
-			__supported_pte_mask &= ~_PAGE_NX;
-		} else {
-			return -EINVAL;
-		}
-	}
 
-	return 0;
+	if (early)
+		__flush_tlb();
+	else
+		flush_tlb_all();
 }
-early_param("noexec", noexec_setup);
-
-static void __init set_nx(void)
-{
-	unsigned int v[4], l, h;
-
-	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
-		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
 
-		if ((v[3] & (1 << 20)) && !disable_nx) {
-			rdmsr(MSR_EFER, l, h);
-			l |= EFER_NX;
-			wrmsr(MSR_EFER, l, h);
-			nx_enabled = 1;
-			__supported_pte_mask |= _PAGE_NX;
-		}
-	}
-}
-#endif
+pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
 
 /* user-defined highmem size */
 static unsigned int highmem_pages = -1;
@@ -631,100 +609,124 @@ static int __init parse_highmem(char *arg)
 }
 early_param("highmem", parse_highmem);
 
+#define MSG_HIGHMEM_TOO_BIG \
+	"highmem size (%luMB) is bigger than pages available (%luMB)!\n"
+
+#define MSG_LOWMEM_TOO_SMALL \
+	"highmem size (%luMB) results in <64MB lowmem, ignoring it!\n"
 /*
- * Determine low and high memory ranges:
+ * All of RAM fits into lowmem - but if user wants highmem
+ * artificially via the highmem=x boot parameter then create
+ * it:
  */
-void __init find_low_pfn_range(void)
+void __init lowmem_pfn_init(void)
 {
-	/* it could update max_pfn */
-
 	/* max_low_pfn is 0, we already have early_res support */
-
 	max_low_pfn = max_pfn;
-	if (max_low_pfn > MAXMEM_PFN) {
-		if (highmem_pages == -1)
-			highmem_pages = max_pfn - MAXMEM_PFN;
-		if (highmem_pages + MAXMEM_PFN < max_pfn)
-			max_pfn = MAXMEM_PFN + highmem_pages;
-		if (highmem_pages + MAXMEM_PFN > max_pfn) {
-			printk(KERN_WARNING "only %luMB highmem pages "
-				"available, ignoring highmem size of %uMB.\n",
-				pages_to_mb(max_pfn - MAXMEM_PFN),
+
+	if (highmem_pages == -1)
+		highmem_pages = 0;
+#ifdef CONFIG_HIGHMEM
+	if (highmem_pages >= max_pfn) {
+		printk(KERN_ERR MSG_HIGHMEM_TOO_BIG,
+			pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
+		highmem_pages = 0;
+	}
+	if (highmem_pages) {
+		if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) {
+			printk(KERN_ERR MSG_LOWMEM_TOO_SMALL,
 				pages_to_mb(highmem_pages));
 			highmem_pages = 0;
 		}
-		max_low_pfn = MAXMEM_PFN;
+		max_low_pfn -= highmem_pages;
+	}
+#else
+	if (highmem_pages)
+		printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
+#endif
+}
+
+#define MSG_HIGHMEM_TOO_SMALL \
+	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
+
+#define MSG_HIGHMEM_TRIMMED \
+	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
+/*
+ * We have more RAM than fits into lowmem - we try to put it into
+ * highmem, also taking the highmem=x boot parameter into account:
+ */
+void __init highmem_pfn_init(void)
+{
+	max_low_pfn = MAXMEM_PFN;
+
+	if (highmem_pages == -1)
+		highmem_pages = max_pfn - MAXMEM_PFN;
+
+	if (highmem_pages + MAXMEM_PFN < max_pfn)
+		max_pfn = MAXMEM_PFN + highmem_pages;
+
+	if (highmem_pages + MAXMEM_PFN > max_pfn) {
+		printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL,
+			pages_to_mb(max_pfn - MAXMEM_PFN),
+			pages_to_mb(highmem_pages));
+		highmem_pages = 0;
+	}
 #ifndef CONFIG_HIGHMEM
-		/* Maximum memory usable is what is directly addressable */
-		printk(KERN_WARNING "Warning only %ldMB will be used.\n",
-					MAXMEM>>20);
-		if (max_pfn > MAX_NONPAE_PFN)
-			printk(KERN_WARNING
-				 "Use a HIGHMEM64G enabled kernel.\n");
-		else
-			printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
-		max_pfn = MAXMEM_PFN;
+	/* Maximum memory usable is what is directly addressable */
+	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
+	if (max_pfn > MAX_NONPAE_PFN)
+		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
+	else
+		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
 #ifndef CONFIG_HIGHMEM64G
-		if (max_pfn > MAX_NONPAE_PFN) {
-			max_pfn = MAX_NONPAE_PFN;
-			printk(KERN_WARNING "Warning only 4GB will be used."
-				"Use a HIGHMEM64G enabled kernel.\n");
-		}
+	if (max_pfn > MAX_NONPAE_PFN) {
+		max_pfn = MAX_NONPAE_PFN;
+		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
+	}
 #endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
-	} else {
-		if (highmem_pages == -1)
-			highmem_pages = 0;
-#ifdef CONFIG_HIGHMEM
-		if (highmem_pages >= max_pfn) {
-			printk(KERN_ERR "highmem size specified (%uMB) is "
-				"bigger than pages available (%luMB)!.\n",
-				pages_to_mb(highmem_pages),
-				pages_to_mb(max_pfn));
-			highmem_pages = 0;
-		}
-		if (highmem_pages) {
-			if (max_low_pfn - highmem_pages <
-			    64*1024*1024/PAGE_SIZE){
-				printk(KERN_ERR "highmem size %uMB results in "
-				"smaller than 64MB lowmem, ignoring it.\n"
-					, pages_to_mb(highmem_pages));
-				highmem_pages = 0;
-			}
-			max_low_pfn -= highmem_pages;
-		}
-#else
-		if (highmem_pages)
-			printk(KERN_ERR "ignoring highmem size on non-highmem"
-					" kernel!\n");
-#endif
-	}
+}
+
+/*
+ * Determine low and high memory ranges:
+ */
+void __init find_low_pfn_range(void)
+{
+	/* it could update max_pfn */
+
+	if (max_pfn <= MAXMEM_PFN)
+		lowmem_pfn_init();
+	else
+		highmem_pfn_init();
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-void __init initmem_init(unsigned long start_pfn,
-				  unsigned long end_pfn)
+void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
+				int acpi, int k8)
 {
 #ifdef CONFIG_HIGHMEM
 	highstart_pfn = highend_pfn = max_pfn;
 	if (max_pfn > max_low_pfn)
 		highstart_pfn = max_low_pfn;
-	memory_present(0, 0, highend_pfn);
 	e820_register_active_regions(0, 0, highend_pfn);
+	sparse_memory_present_with_active_regions(0);
 	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
 		pages_to_mb(highend_pfn - highstart_pfn));
 	num_physpages = highend_pfn;
 	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
 #else
-	memory_present(0, 0, max_low_pfn);
 	e820_register_active_regions(0, 0, max_low_pfn);
+	sparse_memory_present_with_active_regions(0);
 	num_physpages = max_low_pfn;
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
 #ifdef CONFIG_FLATMEM
 	max_mapnr = num_physpages;
 #endif
+	__vmalloc_start_set = true;
+
 	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
 			pages_to_mb(max_low_pfn));
 
@@ -746,166 +748,71 @@ static void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
+#ifndef CONFIG_NO_BOOTMEM
+static unsigned long __init setup_node_bootmem(int nodeid,
+				 unsigned long start_pfn,
+				 unsigned long end_pfn,
+				 unsigned long bootmap)
+{
+	unsigned long bootmap_size;
+
+	/* don't touch min_low_pfn */
+	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
+					 bootmap >> PAGE_SHIFT,
+					 start_pfn, end_pfn);
+	printk(KERN_INFO "  node %d low ram: %08lx - %08lx\n",
+		nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
+	printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
+		 nodeid, bootmap, bootmap + bootmap_size);
+	free_bootmem_with_active_regions(nodeid, end_pfn);
+
+	return bootmap + bootmap_size;
+}
+#endif
+
 void __init setup_bootmem_allocator(void)
 {
-	int i;
+#ifndef CONFIG_NO_BOOTMEM
+	int nodeid;
 	unsigned long bootmap_size, bootmap;
 	/*
 	 * Initialize the boot-time allocator (with low memory only):
 	 */
 	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
-	bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT,
-				 max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
+	bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
 				 PAGE_SIZE);
 	if (bootmap == -1L)
 		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
 	reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
+#endif
 
-	/* don't touch min_low_pfn */
-	bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
-					 min_low_pfn, max_low_pfn);
 	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
 		 max_pfn_mapped<<PAGE_SHIFT);
-	printk(KERN_INFO "  low ram: %08lx - %08lx\n",
-		 min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT);
-	printk(KERN_INFO "  bootmap %08lx - %08lx\n",
-		 bootmap, bootmap + bootmap_size);
-	for_each_online_node(i)
-		free_bootmem_with_active_regions(i, max_low_pfn);
-	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
-
-	after_init_bootmem = 1;
-}
-
-static void __init find_early_table_space(unsigned long end)
-{
-	unsigned long puds, pmds, ptes, tables, start;
-
-	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = PAGE_ALIGN(puds * sizeof(pud_t));
-
-	pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-	tables += PAGE_ALIGN(pmds * sizeof(pmd_t));
-
-	if (cpu_has_pse) {
-		unsigned long extra;
-
-		extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
-		extra += PMD_SIZE;
-		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	} else
-		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
 
-	tables += PAGE_ALIGN(ptes * sizeof(pte_t));
+#ifndef CONFIG_NO_BOOTMEM
+	for_each_online_node(nodeid) {
+		 unsigned long start_pfn, end_pfn;
 
-	/* for fixmap */
-	tables += PAGE_SIZE * 2;
-
-	/*
-	 * RED-PEN putting page tables only on node 0 could
-	 * cause a hotspot and fill up ZONE_DMA. The page tables
-	 * need roughly 0.5KB per GB.
-	 */
-	start = 0x7000;
-	table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
-					tables, PAGE_SIZE);
-	if (table_start == -1UL)
-		panic("Cannot find space for the kernel page tables");
-
-	table_start >>= PAGE_SHIFT;
-	table_end = table_start;
-	table_top = table_start + (tables>>PAGE_SHIFT);
-
-	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, table_start << PAGE_SHIFT,
-		(table_start << PAGE_SHIFT) + tables);
-}
-
-unsigned long __init_refok init_memory_mapping(unsigned long start,
-						unsigned long end)
-{
-	pgd_t *pgd_base = swapper_pg_dir;
-	unsigned long start_pfn, end_pfn;
-	unsigned long big_page_start;
-
-	/*
-	 * Find space for the kernel direct mapping tables.
-	 */
-	if (!after_init_bootmem)
-		find_early_table_space(end);
-
-#ifdef CONFIG_X86_PAE
-	set_nx();
-	if (nx_enabled)
-		printk(KERN_INFO "NX (Execute Disable) protection: active\n");
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+		start_pfn = node_start_pfn[nodeid];
+		end_pfn = node_end_pfn[nodeid];
+		if (start_pfn > max_low_pfn)
+			continue;
+		if (end_pfn > max_low_pfn)
+			end_pfn = max_low_pfn;
+#else
+		start_pfn = 0;
+		end_pfn = max_low_pfn;
 #endif
-
-	/* Enable PSE if available */
-	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
-
-	/* Enable PGE if available */
-	if (cpu_has_pge) {
-		set_in_cr4(X86_CR4_PGE);
-		__supported_pte_mask |= _PAGE_GLOBAL;
+		bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
+						 bootmap);
 	}
+#endif
 
-	/*
-	 * Don't use a large page for the first 2/4MB of memory
-	 * because there are often fixed size MTRRs in there
-	 * and overlapping MTRRs into large pages can cause
-	 * slowdowns.
-	 */
-	big_page_start = PMD_SIZE;
-
-	if (start < big_page_start) {
-		start_pfn = start >> PAGE_SHIFT;
-		end_pfn = min(big_page_start>>PAGE_SHIFT, end>>PAGE_SHIFT);
-	} else {
-		/* head is not big page alignment ? */
-		start_pfn = start >> PAGE_SHIFT;
-		end_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
-				 << (PMD_SHIFT - PAGE_SHIFT);
-	}
-	if (start_pfn < end_pfn)
-		kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, 0);
-
-	/* big page range */
-	start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
-			 << (PMD_SHIFT - PAGE_SHIFT);
-	if (start_pfn < (big_page_start >> PAGE_SHIFT))
-		start_pfn =  big_page_start >> PAGE_SHIFT;
-	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
-	if (start_pfn < end_pfn)
-		kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn,
-						cpu_has_pse);
-
-	/* tail is not big page alignment ? */
-	start_pfn = end_pfn;
-	if (start_pfn > (big_page_start>>PAGE_SHIFT)) {
-		end_pfn = end >> PAGE_SHIFT;
-		if (start_pfn < end_pfn)
-			kernel_physical_mapping_init(pgd_base, start_pfn,
-							 end_pfn, 0);
-	}
-
-	early_ioremap_page_table_range_init(pgd_base);
-
-	load_cr3(swapper_pg_dir);
-
-	__flush_tlb_all();
-
-	if (!after_init_bootmem)
-		reserve_early(table_start << PAGE_SHIFT,
-				 table_end << PAGE_SHIFT, "PGTABLE");
-
-	if (!after_init_bootmem)
-		early_memtest(start, end);
-
-	return end >> PAGE_SHIFT;
+	after_bootmem = 1;
 }
 
-
 /*
  * paging_init() sets up the page tables - note that the first 8MB are
  * already mapped by head.S.
@@ -955,13 +862,13 @@ static void __init test_wp_bit(void)
 	}
 }
 
-static struct kcore_list kcore_mem, kcore_vmalloc;
-
 void __init mem_init(void)
 {
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
+	pci_iommu_alloc();
+
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif
@@ -982,20 +889,15 @@ void __init mem_init(void)
 	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
 	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;
 
-	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
-	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
-		   VMALLOC_END-VMALLOC_START);
-
 	printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, "
 			"%dk reserved, %dk data, %dk init, %ldk highmem)\n",
-		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+		nr_free_pages() << (PAGE_SHIFT-10),
 		num_physpages << (PAGE_SHIFT-10),
 		codesize >> 10,
 		reservedpages << (PAGE_SHIFT-10),
 		datasize >> 10,
 		initsize >> 10,
-		(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
-	       );
+		totalhigh_pages << (PAGE_SHIFT-10));
 
 	printk(KERN_INFO "virtual kernel memory layout:\n"
 		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
@@ -1031,19 +933,32 @@ void __init mem_init(void)
 		(unsigned long)&_text, (unsigned long)&_etext,
 		((unsigned long)&_etext - (unsigned long)&_text) >> 10);
 
+	/*
+	 * Check boundaries twice: Some fundamental inconsistencies can
+	 * be detected at build time already.
+	 */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+#ifdef CONFIG_HIGHMEM
+	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
+	BUILD_BUG_ON(VMALLOC_END			> PKMAP_BASE);
+#endif
+#define high_memory (-128UL << 20)
+	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
+#undef high_memory
+#undef __FIXADDR_TOP
+
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
 	BUG_ON(VMALLOC_END				> PKMAP_BASE);
 #endif
-	BUG_ON(VMALLOC_START				> VMALLOC_END);
+	BUG_ON(VMALLOC_START				>= VMALLOC_END);
 	BUG_ON((unsigned long)high_memory		> VMALLOC_START);
 
 	if (boot_cpu_data.wp_works_ok < 0)
 		test_wp_bit();
 
-	cpa_init();
 	save_pg_dir();
-	zap_low_mappings();
+	zap_low_mappings(true);
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -1054,7 +969,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	return __add_pages(zone, start_pfn, nr_pages);
+	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
 #endif
 
@@ -1086,17 +1001,47 @@ static noinline int do_test_wp_bit(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+int kernel_set_to_readonly __read_mostly;
+
+void set_kernel_text_rw(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read write\n",
+		 start, start+size);
+
+	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read only\n",
+		 start, start+size);
+
+	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long size = PFN_ALIGN(_etext) - start;
 
-#ifndef CONFIG_DYNAMIC_FTRACE
-	/* Dynamic tracing modifies the kernel text section */
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 	printk(KERN_INFO "Write protecting the kernel text: %luk\n",
 		size >> 10);
 
+	kernel_set_to_readonly = 1;
+
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
 		start, start+size);
@@ -1105,7 +1050,6 @@ void mark_rodata_ro(void)
 	printk(KERN_INFO "Testing CPA: write protecting again\n");
 	set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
 #endif
-#endif /* CONFIG_DYNAMIC_FTRACE */
 
 	start += size;
 	size = (unsigned long)__end_rodata - start;
@@ -1124,52 +1068,6 @@ void mark_rodata_ro(void)
 }
 #endif
 
-void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * If debugging page accesses then do not free this memory but
-	 * mark them not present - any buggy init-section access will
-	 * create a kernel page fault:
-	 */
-	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
-	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
-#else
-	unsigned long addr;
-
-	/*
-	 * We just marked the kernel text read only above, now that
-	 * we are going to free part of that, we need to make that
-	 * writeable first.
-	 */
-	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
-
-	for (addr = begin; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
-		totalram_pages++;
-	}
-	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
-#endif
-}
-
-void free_initmem(void)
-{
-	free_init_pages("unused kernel memory",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_init_pages("initrd memory", start, end);
-}
-#endif
-
 int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 				   int flags)
 {