X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=arch%2Fx86%2Fkernel%2Fsetup.c;h=531b55b8e81a1de1827eac5691d5f8aef1d8d10c;hb=734b397cd14f3340394a8dd3266bec97d01f034b;hp=913af838c3c56c3fc4228dc768b11c5a019016e9;hpb=9f248bde9d47cc177011198c9a15fb339b9f3215;p=linux-2.6-omap-h63xx.git

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 913af838c3c..531b55b8e81 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1,337 +1,894 @@
-#include <linux/kernel.h>
+/*
+ *  Copyright (C) 1995  Linus Torvalds
+ *
+ *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ *
+ *  Memory region support
+ *	David Parsons <orc@pell.chi.il.us>, July-August 1999
+ *
+ *  Added E820 sanitization routine (removes overlapping memory regions);
+ *  Brian Moyle <bmoyle@mvista.com>, February 2001
+ *
+ * Moved CPU detection code to cpu/${cpu}.c
+ *    Patrick Mochel <mochel@osdl.org>, March 2002
+ *
+ *  Provisions for empty E820 memory regions (reported by certain BIOSes).
+ *  Alex Achenbach <xela@slit.de>, December 2002.
+ *
+ */
+
+/*
+ * This file handles the architecture-dependent parts of initialization
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/screen_info.h>
+#include <linux/ioport.h>
+#include <linux/acpi.h>
+#include <linux/apm_bios.h>
+#include <linux/initrd.h>
+#include <linux/bootmem.h>
+#include <linux/seq_file.h>
+#include <linux/console.h>
+#include <linux/mca.h>
+#include <linux/root_dev.h>
+#include <linux/highmem.h>
 #include <linux/module.h>
+#include <linux/efi.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
+#include <linux/edd.h>
+#include <linux/iscsi_ibft.h>
+#include <linux/nodemask.h>
+#include <linux/kexec.h>
+#include <linux/dmi.h>
+#include <linux/pfn.h>
+#include <linux/pci.h>
+#include <asm/pci-direct.h>
+#include <linux/init_ohci1394_dma.h>
+#include <linux/kvm_para.h>
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/delay.h>
+#include <linux/highmem.h>
+
+#include <linux/kallsyms.h>
+#include <linux/edd.h>
+#include <linux/iscsi_ibft.h>
+#include <linux/kexec.h>
+#include <linux/cpufreq.h>
+#include <linux/dma-mapping.h>
+#include <linux/ctype.h>
+#include <linux/uaccess.h>
+
 #include <linux/percpu.h>
+#include <linux/crash_dump.h>
+
+#include <video/edid.h>
+
+#include <asm/mtrr.h>
+#include <asm/apic.h>
+#include <asm/e820.h>
+#include <asm/mpspec.h>
+#include <asm/setup.h>
+#include <asm/arch_hooks.h>
+#include <asm/efi.h>
+#include <asm/sections.h>
+#include <asm/dmi.h>
+#include <asm/io_apic.h>
+#include <asm/ist.h>
+#include <asm/vmi.h>
+#include <setup_arch.h>
+#include <asm/bios_ebda.h>
+#include <asm/cacheflush.h>
+#include <asm/processor.h>
+#include <asm/bugs.h>
+
+#include <asm/system.h>
+#include <asm/vsyscall.h>
 #include <asm/smp.h>
+#include <asm/desc.h>
+#include <asm/dma.h>
+#include <asm/gart.h>
+#include <asm/mmu_context.h>
+#include <asm/proto.h>
+
+#include <mach_apic.h>
+#include <asm/paravirt.h>
+
 #include <asm/percpu.h>
 #include <asm/sections.h>
-#include <asm/processor.h>
-#include <asm/setup.h>
 #include <asm/topology.h>
-#include <asm/mpspec.h>
 #include <asm/apicdef.h>
-
-#ifdef CONFIG_X86_LOCAL_APIC
-unsigned int num_processors;
-unsigned disabled_cpus __cpuinitdata;
-/* Processor that is doing the boot up */
-unsigned int boot_cpu_physical_apicid = -1U;
-EXPORT_SYMBOL(boot_cpu_physical_apicid);
-
-/* Bitmask of physically existing CPUs */
-physid_mask_t phys_cpu_present_map;
+#ifdef CONFIG_X86_64
+#include <asm/numa_64.h>
 #endif
 
-/* map cpu index to physical APIC ID */
-DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
-DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
-#define	X86_64_NUMA	1
-
-/* map cpu index to node index */
-DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
-EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
-
-/* which logical CPUs are on which nodes */
-cpumask_t *node_to_cpumask_map;
-EXPORT_SYMBOL(node_to_cpumask_map);
-
-/* setup node_to_cpumask_map */
-static void __init setup_node_to_cpumask_map(void);
+#ifndef ARCH_SETUP
+#define ARCH_SETUP
+#endif
 
+#ifndef CONFIG_DEBUG_BOOT_PARAMS
+struct boot_params __initdata boot_params;
 #else
-static inline void setup_node_to_cpumask_map(void) { }
+struct boot_params boot_params;
 #endif
 
-#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
 /*
- * Copy data used in early init routines from the initial arrays to the
- * per cpu data areas.  These arrays then become expendable and the
- * *_early_ptr's are zeroed indicating that the static arrays are gone.
+ * Machine setup..
  */
-static void __init setup_per_cpu_maps(void)
-{
-	int cpu;
+static struct resource data_resource = {
+	.name	= "Kernel data",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+static struct resource code_resource = {
+	.name	= "Kernel code",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+static struct resource bss_resource = {
+	.name	= "Kernel bss",
+	.start	= 0,
+	.end	= 0,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
 
-	for_each_possible_cpu(cpu) {
-		per_cpu(x86_cpu_to_apicid, cpu) =
-				early_per_cpu_map(x86_cpu_to_apicid, cpu);
-		per_cpu(x86_bios_cpu_apicid, cpu) =
-				early_per_cpu_map(x86_bios_cpu_apicid, cpu);
-#ifdef X86_64_NUMA
-		per_cpu(x86_cpu_to_node_map, cpu) =
-				early_per_cpu_map(x86_cpu_to_node_map, cpu);
-#endif
-	}
 
-	/* indicate the early static arrays will soon be gone */
-	early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
-	early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
-#ifdef X86_64_NUMA
-	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
+#ifdef CONFIG_X86_32
+/* This value is set up by the early boot code to point to the value
+   immediately after the boot time page tables.  It contains a *physical*
+   address, and must not be in the .bss segment! */
+unsigned long init_pg_tables_start __initdata = ~0UL;
+unsigned long init_pg_tables_end __initdata = ~0UL;
+
+static struct resource video_ram_resource = {
+	.name	= "Video RAM area",
+	.start	= 0xa0000,
+	.end	= 0xbffff,
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+/* cpu data as detected by the assembly code in head.S */
+struct cpuinfo_x86 new_cpu_data __cpuinitdata = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+/* common cpu data for all cpus */
+struct cpuinfo_x86 boot_cpu_data __read_mostly = {0, 0, 0, 0, -1, 1, 0, 0, -1};
+EXPORT_SYMBOL(boot_cpu_data);
+static void set_mca_bus(int x)
+{
+#ifdef CONFIG_MCA
+	MCA_bus = x;
 #endif
 }
 
-#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP
-cpumask_t *cpumask_of_cpu_map __read_mostly;
-EXPORT_SYMBOL(cpumask_of_cpu_map);
+unsigned int def_to_bigsmp;
 
-/* requires nr_cpu_ids to be initialized */
-static void __init setup_cpumask_of_cpu(void)
-{
-	int i;
+/* for MCA, but anyone else can use it if they want */
+unsigned int machine_id;
+unsigned int machine_submodel_id;
+unsigned int BIOS_revision;
 
-	/* alloc_bootmem zeroes memory */
-	cpumask_of_cpu_map = alloc_bootmem_low(sizeof(cpumask_t) * nr_cpu_ids);
-	for (i = 0; i < nr_cpu_ids; i++)
-		cpu_set(i, cpumask_of_cpu_map[i]);
-}
+struct apm_info apm_info;
+EXPORT_SYMBOL(apm_info);
+
+#if defined(CONFIG_X86_SPEEDSTEP_SMI) || \
+	defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE)
+struct ist_info ist_info;
+EXPORT_SYMBOL(ist_info);
 #else
-static inline void setup_cpumask_of_cpu(void) { }
+struct ist_info ist_info;
 #endif
 
-#ifdef CONFIG_X86_32
+#else
+struct cpuinfo_x86 boot_cpu_data __read_mostly;
+EXPORT_SYMBOL(boot_cpu_data);
+#endif
+
+
+#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
+unsigned long mmu_cr4_features;
+#else
+unsigned long mmu_cr4_features = X86_CR4_PAE;
+#endif
+
+/* Boot loader ID as an integer, for the benefit of proc_dointvec */
+int bootloader_type;
+
 /*
- * Great future not-so-futuristic plan: make i386 and x86_64 do it
- * the same way
+ * Early DMI memory
  */
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(__per_cpu_offset);
-#endif
+int dmi_alloc_index;
+char dmi_alloc_data[DMI_MAX_DATA];
 
 /*
- * Great future plan:
- * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
- * Always point %gs to its beginning
+ * Setup options
  */
-void __init setup_per_cpu_areas(void)
-{
-	int i, highest_cpu = 0;
-	unsigned long size;
+struct screen_info screen_info;
+EXPORT_SYMBOL(screen_info);
+struct edid_info edid_info;
+EXPORT_SYMBOL_GPL(edid_info);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	prefill_possible_map();
-#endif
+extern int root_mountflags;
 
-	/* Copy section for each CPU (we discard the original) */
-	size = PERCPU_ENOUGH_ROOM;
-	printk(KERN_INFO "PERCPU: Allocating %lu bytes of per cpu data\n",
-			  size);
+unsigned long saved_video_mode;
 
-	for_each_possible_cpu(i) {
-		char *ptr;
-#ifndef CONFIG_NEED_MULTIPLE_NODES
-		ptr = alloc_bootmem_pages(size);
-#else
-		int node = early_cpu_to_node(i);
-		if (!node_online(node) || !NODE_DATA(node)) {
-			ptr = alloc_bootmem_pages(size);
-			printk(KERN_INFO
-			       "cpu %d has no node %d or node-local memory\n",
-				i, node);
-		}
-		else
-			ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
+#define RAMDISK_IMAGE_START_MASK	0x07FF
+#define RAMDISK_PROMPT_FLAG		0x8000
+#define RAMDISK_LOAD_FLAG		0x4000
+
+static char __initdata command_line[COMMAND_LINE_SIZE];
+
+#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
+struct edd edd;
+#ifdef CONFIG_EDD_MODULE
+EXPORT_SYMBOL(edd);
 #endif
-		if (!ptr)
-			panic("Cannot allocate cpu data for CPU %d\n", i);
-#ifdef CONFIG_X86_64
-		cpu_pda(i)->data_offset = ptr - __per_cpu_start;
+/**
+ * copy_edd() - Copy the BIOS EDD information
+ *              from boot_params into a safe place.
+ *
+ */
+static inline void copy_edd(void)
+{
+     memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer,
+	    sizeof(edd.mbr_signature));
+     memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info));
+     edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries;
+     edd.edd_info_nr = boot_params.eddbuf_entries;
+}
 #else
-		__per_cpu_offset[i] = ptr - __per_cpu_start;
+static inline void copy_edd(void)
+{
+}
 #endif
-		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
 
-		highest_cpu = i;
-	}
+#ifdef CONFIG_BLK_DEV_INITRD
 
-	nr_cpu_ids = highest_cpu + 1;
-	printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n",
-		NR_CPUS, nr_cpu_ids, nr_node_ids);
+#ifdef CONFIG_X86_32
 
-	/* Setup percpu data maps */
-	setup_per_cpu_maps();
+#define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
+static void __init relocate_initrd(void)
+{
 
-	/* Setup node to cpumask map */
-	setup_node_to_cpumask_map();
+	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT;
+	u64 ramdisk_here;
+	unsigned long slop, clen, mapaddr;
+	char *p, *q;
+
+	/* We need to move the initrd down into lowmem */
+	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+					 PAGE_SIZE);
+
+	if (ramdisk_here == -1ULL)
+		panic("Cannot find place for new RAMDISK of size %lld\n",
+			 ramdisk_size);
+
+	/* Note: this includes all the lowmem currently occupied by
+	   the initrd, we rely on that fact to keep the data intact. */
+	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+			 "NEW RAMDISK");
+	initrd_start = ramdisk_here + PAGE_OFFSET;
+	initrd_end   = initrd_start + ramdisk_size;
+	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
+			 ramdisk_here, ramdisk_here + ramdisk_size);
+
+	q = (char *)initrd_start;
+
+	/* Copy any lowmem portion of the initrd */
+	if (ramdisk_image < end_of_lowmem) {
+		clen = end_of_lowmem - ramdisk_image;
+		p = (char *)__va(ramdisk_image);
+		memcpy(q, p, clen);
+		q += clen;
+		ramdisk_image += clen;
+		ramdisk_size  -= clen;
+	}
 
-	/* Setup cpumask_of_cpu map */
-	setup_cpumask_of_cpu();
+	/* Copy the highmem portion of the initrd */
+	while (ramdisk_size) {
+		slop = ramdisk_image & ~PAGE_MASK;
+		clen = ramdisk_size;
+		if (clen > MAX_MAP_CHUNK-slop)
+			clen = MAX_MAP_CHUNK-slop;
+		mapaddr = ramdisk_image & PAGE_MASK;
+		p = early_ioremap(mapaddr, clen+slop);
+		memcpy(q, p+slop, clen);
+		early_iounmap(p, clen+slop);
+		q += clen;
+		ramdisk_image += clen;
+		ramdisk_size  -= clen;
+	}
+	/* high pages is not converted by early_res_to_bootmem */
+	ramdisk_image = boot_params.hdr.ramdisk_image;
+	ramdisk_size  = boot_params.hdr.ramdisk_size;
+	printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
+		" %08llx - %08llx\n",
+		ramdisk_image, ramdisk_image + ramdisk_size - 1,
+		ramdisk_here, ramdisk_here + ramdisk_size - 1);
 }
-
 #endif
 
-#ifdef X86_64_NUMA
-
-/*
- * Allocate node_to_cpumask_map based on number of available nodes
- * Requires node_possible_map to be valid.
- *
- * Note: node_to_cpumask() is not valid until after this is done.
- */
-static void __init setup_node_to_cpumask_map(void)
+static void __init reserve_initrd(void)
 {
-	unsigned int node, num = 0;
-	cpumask_t *map;
-
-	/* setup nr_node_ids if not done yet */
-	if (nr_node_ids == MAX_NUMNODES) {
-		for_each_node_mask(node, node_possible_map)
-			num = node;
-		nr_node_ids = num + 1;
+	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 end_of_lowmem = max_low_pfn << PAGE_SHIFT;
+
+	if (!boot_params.hdr.type_of_loader ||
+	    !ramdisk_image || !ramdisk_size)
+		return;		/* No initrd provided by bootloader */
+
+	initrd_start = 0;
+
+	if (ramdisk_size >= (end_of_lowmem>>1)) {
+		free_early(ramdisk_image, ramdisk_end);
+		printk(KERN_ERR "initrd too large to handle, "
+		       "disabling initrd\n");
+		return;
 	}
 
-	/* allocate the map */
-	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
+	printk(KERN_INFO "RAMDISK: %08llx - %08llx\n", ramdisk_image,
+			ramdisk_end);
+
 
-	Dprintk(KERN_DEBUG "Node to cpumask map at %p for %d nodes\n",
-		map, nr_node_ids);
+	if (ramdisk_end <= end_of_lowmem) {
+		/* All in lowmem, easy case */
+		/*
+		 * don't need to reserve again, already reserved early
+		 * in i386_start_kernel
+		 */
+		initrd_start = ramdisk_image + PAGE_OFFSET;
+		initrd_end = initrd_start + ramdisk_size;
+		return;
+	}
 
-	/* node_to_cpumask() will now work */
-	node_to_cpumask_map = map;
+#ifdef CONFIG_X86_32
+	relocate_initrd();
+#else
+	printk(KERN_ERR "initrd extends beyond end of memory "
+	       "(0x%08llx > 0x%08llx)\ndisabling initrd\n",
+	       ramdisk_end, end_of_lowmem);
+	initrd_start = 0;
+#endif
+	free_early(ramdisk_image, ramdisk_end);
+}
+#else
+static void __init reserve_initrd(void)
+{
 }
+#endif /* CONFIG_BLK_DEV_INITRD */
 
-void __cpuinit numa_set_node(int cpu, int node)
+static void __init parse_setup_data(void)
 {
-	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
+	struct setup_data *data;
+	u64 pa_data;
 
-	if (node != NUMA_NO_NODE)
-		cpu_pda(cpu)->nodenumber = node;
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, PAGE_SIZE);
+		switch (data->type) {
+		case SETUP_E820_EXT:
+			parse_e820_ext(data, pa_data);
+			break;
+		default:
+			break;
+		}
+		pa_data = data->next;
+		early_iounmap(data, PAGE_SIZE);
+	}
+}
 
-	if (cpu_to_node_map)
-		cpu_to_node_map[cpu] = node;
+static void __init e820_reserve_setup_data(void)
+{
+	struct setup_data *data;
+	u64 pa_data;
+	int found = 0;
 
-	else if (per_cpu_offset(cpu))
-		per_cpu(x86_cpu_to_node_map, cpu) = node;
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, sizeof(*data));
+		e820_update_range(pa_data, sizeof(*data)+data->len,
+			 E820_RAM, E820_RESERVED_KERN);
+		found = 1;
+		pa_data = data->next;
+		early_iounmap(data, sizeof(*data));
+	}
+	if (!found)
+		return;
 
-	else
-		Dprintk(KERN_INFO "Setting node for non-present cpu %d\n", cpu);
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+	memcpy(&e820_saved, &e820, sizeof(struct e820map));
+	printk(KERN_INFO "extended physical RAM map:\n");
+	e820_print_map("reserve setup_data");
 }
 
-void __cpuinit numa_clear_node(int cpu)
+static void __init reserve_early_setup_data(void)
 {
-	numa_set_node(cpu, NUMA_NO_NODE);
+	struct setup_data *data;
+	u64 pa_data;
+	char buf[32];
+
+	if (boot_params.hdr.version < 0x0209)
+		return;
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, sizeof(*data));
+		sprintf(buf, "setup data %x", data->type);
+		reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf);
+		pa_data = data->next;
+		early_iounmap(data, sizeof(*data));
+	}
 }
 
-#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * --------- Crashkernel reservation ------------------------------
+ */
+
+#ifdef CONFIG_KEXEC
 
-void __cpuinit numa_add_cpu(int cpu)
+/**
+ * Reserve @size bytes of crashkernel memory at any suitable offset.
+ *
+ * @size: Size of the crashkernel memory to reserve.
+ * Returns the base address on success, and -1ULL on failure.
+ */
+unsigned long long find_and_reserve_crashkernel(unsigned long long size)
 {
-	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+	const unsigned long long alignment = 16<<20; 	/* 16M */
+	unsigned long long start = 0LL;
+
+	while (1) {
+		int ret;
+
+		start = find_e820_area(start, ULONG_MAX, size, alignment);
+		if (start == -1ULL)
+			return start;
+
+		/* try to reserve it */
+		ret = reserve_bootmem_generic(start, size, BOOTMEM_EXCLUSIVE);
+		if (ret >= 0)
+			return start;
+
+		start += alignment;
+	}
 }
 
-void __cpuinit numa_remove_cpu(int cpu)
+static inline unsigned long long get_total_mem(void)
 {
-	cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]);
-}
+	unsigned long long total;
 
-#else /* CONFIG_DEBUG_PER_CPU_MAPS */
+	total = max_low_pfn - min_low_pfn;
+#ifdef CONFIG_HIGHMEM
+	total += highend_pfn - highstart_pfn;
+#endif
 
-/*
- * --------- debug versions of the numa functions ---------
- */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+	return total << PAGE_SHIFT;
+}
+
+static void __init reserve_crashkernel(void)
 {
-	int node = cpu_to_node(cpu);
-	cpumask_t *mask;
-	char buf[64];
+	unsigned long long total_mem;
+	unsigned long long crash_size, crash_base;
+	int ret;
 
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_ERR "node_to_cpumask_map NULL\n");
-		dump_stack();
+	total_mem = get_total_mem();
+
+	ret = parse_crashkernel(boot_command_line, total_mem,
+			&crash_size, &crash_base);
+	if (ret != 0 || crash_size <= 0)
 		return;
-	}
 
-	mask = &node_to_cpumask_map[node];
-	if (enable)
-		cpu_set(cpu, *mask);
-	else
-		cpu_clear(cpu, *mask);
+	/* 0 means: find the address automatically */
+	if (crash_base <= 0) {
+		crash_base = find_and_reserve_crashkernel(crash_size);
+		if (crash_base == -1ULL) {
+			pr_info("crashkernel reservation failed. "
+				"No suitable area found.\n");
+			return;
+		}
+	} else {
+		ret = reserve_bootmem_generic(crash_base, crash_size,
+					BOOTMEM_EXCLUSIVE);
+		if (ret < 0) {
+			pr_info("crashkernel reservation failed - "
+				"memory is in use\n");
+			return;
+		}
+	}
 
-	cpulist_scnprintf(buf, sizeof(buf), *mask);
-	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
-		enable? "numa_add_cpu":"numa_remove_cpu", cpu, node, buf);
- }
+	printk(KERN_INFO "Reserving %ldMB of memory at %ldMB "
+			"for crashkernel (System RAM: %ldMB)\n",
+			(unsigned long)(crash_size >> 20),
+			(unsigned long)(crash_base >> 20),
+			(unsigned long)(total_mem >> 20));
 
-void __cpuinit numa_add_cpu(int cpu)
-{
-	numa_set_cpumask(cpu, 1);
+	crashk_res.start = crash_base;
+	crashk_res.end   = crash_base + crash_size - 1;
+	insert_resource(&iomem_resource, &crashk_res);
 }
-
-void __cpuinit numa_remove_cpu(int cpu)
+#else
+static void __init reserve_crashkernel(void)
 {
-	numa_set_cpumask(cpu, 0);
 }
+#endif
 
-int cpu_to_node(int cpu)
+static struct resource standard_io_resources[] = {
+	{ .name = "dma1", .start = 0x00, .end = 0x1f,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "pic1", .start = 0x20, .end = 0x21,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "timer0", .start = 0x40, .end = 0x43,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "timer1", .start = 0x50, .end = 0x53,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "keyboard", .start = 0x60, .end = 0x60,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "keyboard", .start = 0x64, .end = 0x64,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "dma page reg", .start = 0x80, .end = 0x8f,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "pic2", .start = 0xa0, .end = 0xa1,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "dma2", .start = 0xc0, .end = 0xdf,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO },
+	{ .name = "fpu", .start = 0xf0, .end = 0xff,
+		.flags = IORESOURCE_BUSY | IORESOURCE_IO }
+};
+
+static void __init reserve_standard_io_resources(void)
 {
-	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
-		printk(KERN_WARNING
-			"cpu_to_node(%d): usage too early!\n", cpu);
-		dump_stack();
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-	}
-	return per_cpu(x86_cpu_to_node_map, cpu);
+	int i;
+
+	/* request I/O space for devices used on all i[345]86 PCs */
+	for (i = 0; i < ARRAY_SIZE(standard_io_resources); i++)
+		request_resource(&ioport_resource, &standard_io_resources[i]);
+
 }
-EXPORT_SYMBOL(cpu_to_node);
 
-/*
- * Same function as cpu_to_node() but used if called before the
- * per_cpu areas are setup.
+#ifdef CONFIG_PROC_VMCORE
+/* elfcorehdr= specifies the location of elf core header
+ * stored by the crashed kernel. This option will be passed
+ * by kexec loader to the capture kernel.
  */
-int early_cpu_to_node(int cpu)
+static int __init setup_elfcorehdr(char *arg)
 {
-	if (early_per_cpu_ptr(x86_cpu_to_node_map))
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
-	if (!per_cpu_offset(cpu)) {
-		printk(KERN_WARNING
-			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
-		dump_stack();
-		return NUMA_NO_NODE;
-	}
-	return per_cpu(x86_cpu_to_node_map, cpu);
+	char *end;
+	if (!arg)
+		return -EINVAL;
+	elfcorehdr_addr = memparse(arg, &end);
+	return end > arg ? 0 : -EINVAL;
 }
+early_param("elfcorehdr", setup_elfcorehdr);
+#endif
 
 /*
- * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ * Determine if we were loaded by an EFI loader.  If so, then we have also been
+ * passed the efi memmap, systab, etc., so we should use these data structures
+ * for initialization.  Note, the efi init code path is determined by the
+ * global efi_enabled. This allows the same kernel image to be used on existing
+ * systems (with a traditional BIOS) as well as on EFI systems.
  */
-cpumask_t *_node_to_cpumask_ptr(int node)
-{
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"_node_to_cpumask_ptr(%d): no node_to_cpumask_map!\n",
-			node);
-		dump_stack();
-		return &cpu_online_map;
-	}
-	return &node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(_node_to_cpumask_ptr);
-
 /*
- * Returns a bitmask of CPUs on Node 'node'.
+ * setup_arch - architecture-specific boot-time initializations
+ *
+ * Note: On x86_64, fixmaps are ready for use even before this is called.
  */
-cpumask_t node_to_cpumask(int node)
+
+void __init setup_arch(char **cmdline_p)
 {
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
-		dump_stack();
-		return cpu_online_map;
+#ifdef CONFIG_X86_32
+	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
+	visws_early_detect();
+	pre_setup_arch_hook();
+	early_cpu_init();
+#else
+	printk(KERN_INFO "Command line: %s\n", boot_command_line);
+#endif
+
+	early_ioremap_init();
+
+	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
+	screen_info = boot_params.screen_info;
+	edid_info = boot_params.edid_info;
+#ifdef CONFIG_X86_32
+	apm_info.bios = boot_params.apm_bios_info;
+	ist_info = boot_params.ist_info;
+	if (boot_params.sys_desc_table.length != 0) {
+		set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2);
+		machine_id = boot_params.sys_desc_table.table[0];
+		machine_submodel_id = boot_params.sys_desc_table.table[1];
+		BIOS_revision = boot_params.sys_desc_table.table[2];
 	}
-	return node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(node_to_cpumask);
+#endif
+	saved_video_mode = boot_params.hdr.vid_mode;
+	bootloader_type = boot_params.hdr.type_of_loader;
 
-/*
- * --------- end of debug versions of the numa functions ---------
- */
+#ifdef CONFIG_BLK_DEV_RAM
+	rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
+	rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
+	rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
+#endif
+#ifdef CONFIG_EFI
+	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
+#ifdef CONFIG_X86_32
+		     "EL32",
+#else
+		     "EL64",
+#endif
+	 4)) {
+		efi_enabled = 1;
+		efi_reserve_early();
+	}
+#endif
+
+	ARCH_SETUP
+
+	setup_memory_map();
+	parse_setup_data();
+	/* update the e820_saved too */
+	e820_reserve_setup_data();
+
+	copy_edd();
+
+	if (!boot_params.hdr.root_flags)
+		root_mountflags &= ~MS_RDONLY;
+	init_mm.start_code = (unsigned long) _text;
+	init_mm.end_code = (unsigned long) _etext;
+	init_mm.end_data = (unsigned long) _edata;
+#ifdef CONFIG_X86_32
+	init_mm.brk = init_pg_tables_end + PAGE_OFFSET;
+#else
+	init_mm.brk = (unsigned long) &_end;
+#endif
+
+	code_resource.start = virt_to_phys(_text);
+	code_resource.end = virt_to_phys(_etext)-1;
+	data_resource.start = virt_to_phys(_etext);
+	data_resource.end = virt_to_phys(_edata)-1;
+	bss_resource.start = virt_to_phys(&__bss_start);
+	bss_resource.end = virt_to_phys(&__bss_stop)-1;
+
+#ifdef CONFIG_X86_64
+	early_cpu_init();
+#endif
+	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+	*cmdline_p = command_line;
+
+	parse_early_param();
+
+	/* after early param, so could get panic from serial */
+	reserve_early_setup_data();
+
+	if (acpi_mps_check()) {
+#ifdef CONFIG_X86_LOCAL_APIC
+		disable_apic = 1;
+#endif
+		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+	}
+
+#ifdef CONFIG_PCI
+	if (pci_early_dump_regs)
+		early_dump_pci_devices();
+#endif
+
+	finish_e820_parsing();
+
+#ifdef CONFIG_X86_32
+	probe_roms();
+#endif
+
+	/* after parse_early_param, so could debug it */
+	insert_resource(&iomem_resource, &code_resource);
+	insert_resource(&iomem_resource, &data_resource);
+	insert_resource(&iomem_resource, &bss_resource);
+
+	if (efi_enabled)
+		efi_init();
+
+#ifdef CONFIG_X86_32
+	if (ppro_with_ram_bug()) {
+		e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
+				  E820_RESERVED);
+		sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+		printk(KERN_INFO "fixed physical RAM map:\n");
+		e820_print_map("bad_ppro");
+	}
+#else
+	early_gart_iommu_check();
+#endif
+
+	/*
+	 * partially used pages are not usable - thus
+	 * we are rounding upwards:
+	 */
+	max_pfn = e820_end_of_ram_pfn();
 
-#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
+	/* preallocate 4k for mptable mpc */
+	early_reserve_e820_mpc_new();
+	/* update e820 for memory not covered by WB MTRRs */
+	mtrr_bp_init();
+	if (mtrr_trim_uncached_memory(max_pfn))
+		max_pfn = e820_end_of_ram_pfn();
 
-#endif /* X86_64_NUMA */
+#ifdef CONFIG_X86_32
+	/* max_low_pfn get updated here */
+	find_low_pfn_range();
+#else
+	num_physpages = max_pfn;
+
+	check_efer();
+
+	/* How many end-of-memory variables you have, grandma! */
+	/* need this before calling reserve_initrd */
+	if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
+		max_low_pfn = e820_end_of_low_ram_pfn();
+	else
+		max_low_pfn = max_pfn;
+
+	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+#endif
+
+	/* max_pfn_mapped is updated here */
+	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
+	max_pfn_mapped = max_low_pfn_mapped;
+
+#ifdef CONFIG_X86_64
+	if (max_pfn > max_low_pfn) {
+		max_pfn_mapped = init_memory_mapping(1UL<<32,
+						     max_pfn<<PAGE_SHIFT);
+		/* can we preseve max_low_pfn ?*/
+		max_low_pfn = max_pfn;
+	}
+#endif
+
+	/*
+	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.
+	 */
+
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	if (init_ohci1394_dma_early)
+		init_ohci1394_dma_on_all_controllers();
+#endif
+
+	reserve_initrd();
+
+#ifdef CONFIG_X86_64
+	vsmp_init();
+#endif
+
+	dmi_scan_machine();
+
+	io_delay_init();
+
+	/*
+	 * Parse the ACPI tables for possible boot-time SMP configuration.
+	 */
+	acpi_boot_table_init();
+
+#ifdef CONFIG_ACPI_NUMA
+	/*
+	 * Parse SRAT to discover nodes.
+	 */
+	acpi_numa_init();
+#endif
+
+	initmem_init(0, max_pfn);
+
+#ifdef CONFIG_X86_64
+	dma32_reserve_bootmem();
+#endif
+
+#ifdef CONFIG_ACPI_SLEEP
+	/*
+	 * Reserve low memory region for sleep support.
+	 */
+	acpi_reserve_bootmem();
+#endif
+#ifdef CONFIG_X86_FIND_SMP_CONFIG
+	/*
+	 * Find and reserve possible boot-time SMP configuration:
+	 */
+	find_smp_config();
+#endif
+	reserve_crashkernel();
+
+	reserve_ibft_region();
+
+#ifdef CONFIG_KVM_CLOCK
+	kvmclock_init();
+#endif
+
+#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
+	/*
+	 * Must be after max_low_pfn is determined, and before kernel
+	 * pagetables are setup.
+	 */
+	vmi_init();
+#endif
+
+	paging_init();
+
+#ifdef CONFIG_X86_64
+	map_vsyscall();
+#endif
+
+#ifdef CONFIG_X86_GENERICARCH
+	generic_apic_probe();
+#endif
+
+	early_quirks();
+
+	/*
+	 * Read APIC and some other early information from ACPI tables.
+	 */
+	acpi_boot_init();
+
+#if defined(CONFIG_X86_MPPARSE) || defined(CONFIG_X86_VISWS)
+	/*
+	 * get boot-time SMP configuration:
+	 */
+	if (smp_found_config)
+		get_smp_config();
+#endif
+
+	prefill_possible_map();
+#ifdef CONFIG_X86_64
+	init_cpu_to_node();
+#endif
+
+#ifdef CONFIG_X86_NUMAQ
+	/*
+	 * need to check online nodes num, call it
+	 * here before time_init/tsc_init
+	 */
+	numaq_tsc_disable();
+#endif
+
+	init_apic_mappings();
+	ioapic_init_mappings();
+
+#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) && defined(CONFIG_X86_32)
+	if (def_to_bigsmp)
+		printk(KERN_WARNING "More than 8 CPUs detected and "
+			"CONFIG_X86_PC cannot handle it.\nUse "
+			"CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
+#endif
+	kvm_guest_init();
+
+	e820_reserve_resources();
+	e820_mark_nosave_regions(max_low_pfn);
+
+#ifdef CONFIG_X86_32
+	request_resource(&iomem_resource, &video_ram_resource);
+#endif
+	reserve_standard_io_resources();
+
+	e820_setup_gap();
+
+#ifdef CONFIG_VT
+#if defined(CONFIG_VGA_CONSOLE)
+	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+		conswitchp = &vga_con;
+#elif defined(CONFIG_DUMMY_CONSOLE)
+	conswitchp = &dummy_con;
+#endif
+#endif
+}