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 <linux/smp.h>
#include <linux/topology.h>
#include <linux/pfn.h>
#include <asm/sections.h>
#include <asm/processor.h>
#include <asm/setup.h>
#include <asm/mpspec.h>
#include <asm/apicdef.h>
#include <asm/highmem.h>
#include <asm/proto.h>
#include <asm/cpumask.h>
#include <asm/cpu.h>
#include <asm/stackprotector.h>

#ifdef CONFIG_DEBUG_PER_CPU_MAPS
# define DBG(x...) printk(KERN_DEBUG x)
#else
# define DBG(x...)
#endif

DEFINE_PER_CPU(int, cpu_number);
EXPORT_PER_CPU_SYMBOL(cpu_number);

#ifdef CONFIG_X86_64
#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
#else
#define BOOT_PERCPU_OFFSET 0
#endif

DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
EXPORT_PER_CPU_SYMBOL(this_cpu_off);

unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
};
EXPORT_SYMBOL(__per_cpu_offset);

/*
 * On x86_64 symbols referenced from code should be reachable using
 * 32bit relocations.  Reserve space for static percpu variables in
 * modules so that they are always served from the first chunk which
 * is located at the percpu segment base.  On x86_32, anything can
 * address anywhere.  No need to reserve space in the first chunk.
 */
#ifdef CONFIG_X86_64
#define PERCPU_FIRST_CHUNK_RESERVE	PERCPU_MODULE_RESERVE
#else
#define PERCPU_FIRST_CHUNK_RESERVE	0
#endif

/**
 * pcpu_need_numa - determine percpu allocation needs to consider NUMA
 *
 * If NUMA is not configured or there is only one NUMA node available,
 * there is no reason to consider NUMA.  This function determines
 * whether percpu allocation should consider NUMA or not.
 *
 * RETURNS:
 * true if NUMA should be considered; otherwise, false.
 */
static bool __init pcpu_need_numa(void)
{
#ifdef CONFIG_NEED_MULTIPLE_NODES
	pg_data_t *last = NULL;
	unsigned int cpu;

	for_each_possible_cpu(cpu) {
		int node = early_cpu_to_node(cpu);

		if (node_online(node) && NODE_DATA(node) &&
		    last && last != NODE_DATA(node))
			return true;

		last = NODE_DATA(node);
	}
#endif
	return false;
}

/**
 * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
 * @cpu: cpu to allocate for
 * @size: size allocation in bytes
 * @align: alignment
 *
 * Allocate @size bytes aligned at @align for cpu @cpu.  This wrapper
 * does the right thing for NUMA regardless of the current
 * configuration.
 *
 * RETURNS:
 * Pointer to the allocated area on success, NULL on failure.
 */
static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
					unsigned long align)
{
	const unsigned long goal = __pa(MAX_DMA_ADDRESS);
#ifdef CONFIG_NEED_MULTIPLE_NODES
	int node = early_cpu_to_node(cpu);
	void *ptr;

	if (!node_online(node) || !NODE_DATA(node)) {
		ptr = __alloc_bootmem_nopanic(size, align, goal);
		pr_info("cpu %d has no node %d or node-local memory\n",
			cpu, node);
		pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
			 cpu, size, __pa(ptr));
	} else {
		ptr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
						   size, align, goal);
		pr_debug("per cpu data for cpu%d %lu bytes on node%d at "
			 "%016lx\n", cpu, size, node, __pa(ptr));
	}
	return ptr;
#else
	return __alloc_bootmem_nopanic(size, align, goal);
#endif
}

/*
 * Helpers for first chunk memory allocation
 */
static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
{
	return pcpu_alloc_bootmem(cpu, size, align);
}

static void __init pcpu_fc_free(void *ptr, size_t size)
{
	free_bootmem(__pa(ptr), size);
}

/*
 * Large page remapping allocator
 */
#ifdef CONFIG_NEED_MULTIPLE_NODES
static void __init pcpul_map(void *ptr, size_t size, void *addr)
{
	pmd_t *pmd, pmd_v;

	pmd = populate_extra_pmd((unsigned long)addr);
	pmd_v = pfn_pmd(page_to_pfn(virt_to_page(ptr)), PAGE_KERNEL_LARGE);
	set_pmd(pmd, pmd_v);
}

static int pcpu_lpage_cpu_distance(unsigned int from, unsigned int to)
{
	if (early_cpu_to_node(from) == early_cpu_to_node(to))
		return LOCAL_DISTANCE;
	else
		return REMOTE_DISTANCE;
}

static ssize_t __init setup_pcpu_lpage(bool chosen)
{
	size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
	size_t dyn_size = reserve - PERCPU_FIRST_CHUNK_RESERVE;
	struct pcpu_alloc_info *ai;
	ssize_t ret;

	/* on non-NUMA, embedding is better */
	if (!chosen && !pcpu_need_numa())
		return -EINVAL;

	/* need PSE */
	if (!cpu_has_pse) {
		pr_warning("PERCPU: lpage allocator requires PSE\n");
		return -EINVAL;
	}

	/* allocate and build unit_map */
	ai = pcpu_build_alloc_info(PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
				   PMD_SIZE, pcpu_lpage_cpu_distance);
	if (IS_ERR(ai)) {
		pr_warning("PERCPU: failed to build unit_map (%ld)\n",
			   PTR_ERR(ai));
		return PTR_ERR(ai);
	}

	/* do the parameters look okay? */
	if (!chosen) {
		size_t vm_size = VMALLOC_END - VMALLOC_START;
		size_t tot_size = 0;
		int group;

		for (group = 0; group < ai->nr_groups; group++)
			tot_size += ai->unit_size * ai->groups[group].nr_units;

		/* don't consume more than 20% of vmalloc area */
		if (tot_size > vm_size / 5) {
			pr_info("PERCPU: too large chunk size %zuMB for "
				"large page remap\n", tot_size >> 20);
			ret = -EINVAL;
			goto out_free;
		}
	}

	ret = pcpu_lpage_first_chunk(ai, pcpu_fc_alloc, pcpu_fc_free,
				     pcpul_map);
out_free:
	pcpu_free_alloc_info(ai);
	return ret;
}
#else
static ssize_t __init setup_pcpu_lpage(bool chosen)
{
	return -EINVAL;
}
#endif

/*
 * Embedding allocator
 *
 * The first chunk is sized to just contain the static area plus
 * module and dynamic reserves and embedded into linear physical
 * mapping so that it can use PMD mapping without additional TLB
 * pressure.
 */
static ssize_t __init setup_pcpu_embed(bool chosen)
{
	size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;

	/*
	 * If large page isn't supported, there's no benefit in doing
	 * this.  Also, embedding allocation doesn't play well with
	 * NUMA.
	 */
	if (!chosen && (!cpu_has_pse || pcpu_need_numa()))
		return -EINVAL;

	return pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
				      reserve - PERCPU_FIRST_CHUNK_RESERVE);
}

/*
 * Page allocator
 *
 * Boring fallback 4k page allocator.  This allocator puts more
 * pressure on PTE TLBs but other than that behaves nicely on both UMA
 * and NUMA.
 */
static void __init pcpup_populate_pte(unsigned long addr)
{
	populate_extra_pte(addr);
}

static ssize_t __init setup_pcpu_page(void)
{
	return pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
				     pcpu_fc_alloc, pcpu_fc_free,
				     pcpup_populate_pte);
}

static inline void setup_percpu_segment(int cpu)
{
#ifdef CONFIG_X86_32
	struct desc_struct gdt;

	pack_descriptor(&gdt, per_cpu_offset(cpu), 0xFFFFF,
			0x2 | DESCTYPE_S, 0x8);
	gdt.s = 1;
	write_gdt_entry(get_cpu_gdt_table(cpu),
			GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
#endif
}

void __init setup_per_cpu_areas(void)
{
	unsigned int cpu;
	unsigned long delta;
	size_t pcpu_unit_size;
	ssize_t ret;

	pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
		NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);

	/*
	 * Allocate percpu area.  If PSE is supported, try to make use
	 * of large page mappings.  Please read comments on top of
	 * each allocator for details.
	 */
	ret = -EINVAL;
	if (pcpu_chosen_fc != PCPU_FC_AUTO) {
		if (pcpu_chosen_fc != PCPU_FC_PAGE) {
			if (pcpu_chosen_fc == PCPU_FC_LPAGE)
				ret = setup_pcpu_lpage(true);
			else
				ret = setup_pcpu_embed(true);

			if (ret < 0)
				pr_warning("PERCPU: %s allocator failed (%zd), "
					   "falling back to page size\n",
					   pcpu_fc_names[pcpu_chosen_fc], ret);
		}
	} else {
		ret = setup_pcpu_lpage(false);
		if (ret < 0)
			ret = setup_pcpu_embed(false);
	}
	if (ret < 0)
		ret = setup_pcpu_page();
	if (ret < 0)
		panic("cannot initialize percpu area (err=%zd)", ret);

	pcpu_unit_size = ret;

	/* alrighty, percpu areas up and running */
	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
	for_each_possible_cpu(cpu) {
		per_cpu_offset(cpu) =
			delta + pcpu_unit_map[cpu] * pcpu_unit_size;
		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
		per_cpu(cpu_number, cpu) = cpu;
		setup_percpu_segment(cpu);
		setup_stack_canary_segment(cpu);
		/*
		 * 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.
		 */
#ifdef CONFIG_X86_LOCAL_APIC
		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);
#endif
#ifdef CONFIG_X86_64
		per_cpu(irq_stack_ptr, cpu) =
			per_cpu(irq_stack_union.irq_stack, cpu) +
			IRQ_STACK_SIZE - 64;
#ifdef CONFIG_NUMA
		per_cpu(x86_cpu_to_node_map, cpu) =
			early_per_cpu_map(x86_cpu_to_node_map, cpu);
#endif
#endif
		/*
		 * Up to this point, the boot CPU has been using .data.init
		 * area.  Reload any changed state for the boot CPU.
		 */
		if (cpu == boot_cpu_id)
			switch_to_new_gdt(cpu);
	}

	/* indicate the early static arrays will soon be gone */
#ifdef CONFIG_X86_LOCAL_APIC
	early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
	early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
#endif
#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
#endif

#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
	/*
	 * make sure boot cpu node_number is right, when boot cpu is on the
	 * node that doesn't have mem installed
	 */
	per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id);
#endif

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

	/* Setup cpu initialized, callin, callout masks */
	setup_cpu_local_masks();
}