arch/x86/kernel/setup_percpu.c

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/percpu.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
#include <asm/smp.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>
#include <asm/highmem.h>

#ifndef CONFIG_DEBUG_BOOT_PARAMS
struct boot_params __initdata boot_params;
#else
struct boot_params boot_params;
#endif

#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;
unsigned int max_physical_apicid;
EXPORT_SYMBOL(boot_cpu_physical_apicid);

/* Bitmask of physically existing CPUs */
physid_mask_t phys_cpu_present_map;
#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);

#else
static inline void setup_node_to_cpumask_map(void) { }
#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.
 */
static void __init setup_per_cpu_maps(void)
{
	int cpu;

	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;
#endif
}

#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP
cpumask_t *cpumask_of_cpu_map __read_mostly;
EXPORT_SYMBOL(cpumask_of_cpu_map);

/* requires nr_cpu_ids to be initialized */
static void __init setup_cpumask_of_cpu(void)
{
	int i;

	/* 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]);
}
#else
static inline void setup_cpumask_of_cpu(void) { }
#endif

#ifdef CONFIG_X86_32
/*
 * Great future not-so-futuristic plan: make i386 and x86_64 do it
 * the same way
 */
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
static inline void setup_cpu_pda_map(void) { }

#elif !defined(CONFIG_SMP)
static inline void setup_cpu_pda_map(void) { }

#else /* CONFIG_SMP && CONFIG_X86_64 */

/*
 * Allocate cpu_pda pointer table and array via alloc_bootmem.
 */
static void __init setup_cpu_pda_map(void)
{
	char *pda;
	struct x8664_pda **new_cpu_pda;
	unsigned long size;
	int cpu;

	size = roundup(sizeof(struct x8664_pda), cache_line_size());

	/* allocate cpu_pda array and pointer table */
	{
		unsigned long tsize = nr_cpu_ids * sizeof(void *);
		unsigned long asize = size * (nr_cpu_ids - 1);

		tsize = roundup(tsize, cache_line_size());
		new_cpu_pda = alloc_bootmem(tsize + asize);
		pda = (char *)new_cpu_pda + tsize;
	}

	/* initialize pointer table to static pda's */
	for_each_possible_cpu(cpu) {
		if (cpu == 0) {
			/* leave boot cpu pda in place */
			new_cpu_pda[0] = cpu_pda(0);
			continue;
		}
		new_cpu_pda[cpu] = (struct x8664_pda *)pda;
		new_cpu_pda[cpu]->in_bootmem = 1;
		pda += size;
	}

	/* point to new pointer table */
	_cpu_pda = new_cpu_pda;
}
#endif

/*
 * Great future plan:
 * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
 * Always point %gs to its beginning
 */
void __init setup_per_cpu_areas(void)
{
	ssize_t size = PERCPU_ENOUGH_ROOM;
	char *ptr;
	int cpu;

	/* no processor from mptable or madt */
	if (!num_processors)
		num_processors = 1;

#ifdef CONFIG_HOTPLUG_CPU
	prefill_possible_map();
#else
	nr_cpu_ids = num_processors;
#endif

	/* Setup cpu_pda map */
	setup_cpu_pda_map();

	/* Copy section for each CPU (we discard the original) */
	size = PERCPU_ENOUGH_ROOM;
	printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
			  size);

	for_each_possible_cpu(cpu) {
#ifndef CONFIG_NEED_MULTIPLE_NODES
		ptr = alloc_bootmem_pages(size);
#else
		int node = early_cpu_to_node(cpu);
		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",
				cpu, node);
		}
		else
			ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
#endif
		per_cpu_offset(cpu) = ptr - __per_cpu_start;
		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);

	}

	printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n",
		NR_CPUS, nr_cpu_ids, nr_node_ids);

	/* Setup percpu data maps */
	setup_per_cpu_maps();

	/* Setup node to cpumask map */
	setup_node_to_cpumask_map();

	/* Setup cpumask_of_cpu map */
	setup_cpumask_of_cpu();
}

#endif

void __init parse_setup_data(void)
{
	struct setup_data *data;
	u64 pa_data;

	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;
		}
#ifndef CONFIG_DEBUG_BOOT_PARAMS
		free_early(pa_data, pa_data+sizeof(*data)+data->len);
#endif
		pa_data = data->next;
		early_iounmap(data, PAGE_SIZE);
	}
}

#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)
{
	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;
	}

	/* allocate the map */
	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));

	Dprintk(KERN_DEBUG "Node to cpumask map at %p for %d nodes\n",
		map, nr_node_ids);

	/* node_to_cpumask() will now work */
	node_to_cpumask_map = map;
}

void __cpuinit numa_set_node(int cpu, int node)
{
	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);

	if (cpu_pda(cpu) && node != NUMA_NO_NODE)
		cpu_pda(cpu)->nodenumber = node;

	if (cpu_to_node_map)
		cpu_to_node_map[cpu] = node;

	else if (per_cpu_offset(cpu))
		per_cpu(x86_cpu_to_node_map, cpu) = node;

	else
		Dprintk(KERN_INFO "Setting node for non-present cpu %d\n", cpu);
}

void __cpuinit numa_clear_node(int cpu)
{
	numa_set_node(cpu, NUMA_NO_NODE);
}

#ifndef CONFIG_DEBUG_PER_CPU_MAPS

void __cpuinit numa_add_cpu(int cpu)
{
	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}

void __cpuinit numa_remove_cpu(int cpu)
{
	cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]);
}

#else /* CONFIG_DEBUG_PER_CPU_MAPS */

/*
 * --------- debug versions of the numa functions ---------
 */
static void __cpuinit numa_set_cpumask(int cpu, int enable)
{
	int node = cpu_to_node(cpu);
	cpumask_t *mask;
	char buf[64];

	if (node_to_cpumask_map == NULL) {
		printk(KERN_ERR "node_to_cpumask_map NULL\n");
		dump_stack();
		return;
	}

	mask = &node_to_cpumask_map[node];
	if (enable)
		cpu_set(cpu, *mask);
	else
		cpu_clear(cpu, *mask);

	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);
 }

void __cpuinit numa_add_cpu(int cpu)
{
	numa_set_cpumask(cpu, 1);
}

void __cpuinit numa_remove_cpu(int cpu)
{
	numa_set_cpumask(cpu, 0);
}

int cpu_to_node(int cpu)
{
	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);
}
EXPORT_SYMBOL(cpu_to_node);

/*
 * Same function as cpu_to_node() but used if called before the
 * per_cpu areas are setup.
 */
int early_cpu_to_node(int cpu)
{
	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);
}

/*
 * Returns a pointer to the bitmask of CPUs on Node 'node'.
 */
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;
	}
	BUG_ON(node >= nr_node_ids);
	return &node_to_cpumask_map[node];
}
EXPORT_SYMBOL(_node_to_cpumask_ptr);

/*
 * Returns a bitmask of CPUs on Node 'node'.
 */
cpumask_t node_to_cpumask(int node)
{
	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;
	}
	BUG_ON(node >= nr_node_ids);
	return node_to_cpumask_map[node];
}
EXPORT_SYMBOL(node_to_cpumask);

/*
 * --------- end of debug versions of the numa functions ---------
 */

#endif /* CONFIG_DEBUG_PER_CPU_MAPS */

#endif /* X86_64_NUMA */


/*
 * --------- Crashkernel reservation ------------------------------
 */

static inline unsigned long long get_total_mem(void)
{
	unsigned long long total;

	total = max_low_pfn - min_low_pfn;
#ifdef CONFIG_HIGHMEM
	total += highend_pfn - highstart_pfn;
#endif

	return total << PAGE_SHIFT;
}

#ifdef CONFIG_KEXEC
void __init reserve_crashkernel(void)
{
	unsigned long long total_mem;
	unsigned long long crash_size, crash_base;
	int ret;

	total_mem = get_total_mem();

	ret = parse_crashkernel(boot_command_line, total_mem,
			&crash_size, &crash_base);
	if (ret == 0 && crash_size > 0) {
		if (crash_base <= 0) {
			printk(KERN_INFO "crashkernel reservation failed - "
					"you have to specify a base address\n");
			return;
		}

		if (reserve_bootmem_generic(crash_base, crash_size,
					BOOTMEM_EXCLUSIVE) < 0) {
			printk(KERN_INFO "crashkernel reservation failed - "
					"memory is in use\n");
			return;
		}

		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));

		crashk_res.start = crash_base;
		crashk_res.end   = crash_base + crash_size - 1;
		insert_resource(&iomem_resource, &crashk_res);
	}
}
#else
void __init reserve_crashkernel(void)
{}
#endif
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 }
};

void __init reserve_standard_io_resources(void)
{
	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]);

}

#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.
 */
static int __init setup_elfcorehdr(char *arg)
{
	char *end;
	if (!arg)
		return -EINVAL;
	elfcorehdr_addr = memparse(arg, &end);
	return end > arg ? 0 : -EINVAL;
}
early_param("elfcorehdr", setup_elfcorehdr);
#endif