percpu.c

Go to the documentation of this file.

/*
 * mm/percpu.c - percpu memory allocator
 *
 * Copyright (C) 2009       SUSE Linux Products GmbH
 * Copyright (C) 2009       Tejun Heo <[email protected]>
 *
 * This file is released under the GPLv2.
 *
 * This is percpu allocator which can handle both static and dynamic
 * areas.  Percpu areas are allocated in chunks.  Each chunk is
 * consisted of boot-time determined number of units and the first
 * chunk is used for static percpu variables in the kernel image
 * (special boot time alloc/init handling necessary as these areas
 * need to be brought up before allocation services are running).
 * Unit grows as necessary and all units grow or shrink in unison.
 * When a chunk is filled up, another chunk is allocated.
 *
 *  c0                           c1                         c2
 *  -------------------          -------------------        ------------
 * | u0 | u1 | u2 | u3 |        | u0 | u1 | u2 | u3 |      | u0 | u1 | u
 *  -------------------  ......  -------------------  ....  ------------
 *
 * Allocation is done in offset-size areas of single unit space.  Ie,
 * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0,
 * c1:u1, c1:u2 and c1:u3.  On UMA, units corresponds directly to
 * cpus.  On NUMA, the mapping can be non-linear and even sparse.
 * Percpu access can be done by configuring percpu base registers
 * according to cpu to unit mapping and pcpu_unit_size.
 *
 * There are usually many small percpu allocations many of them being
 * as small as 4 bytes.  The allocator organizes chunks into lists
 * according to free size and tries to allocate from the fullest one.
 * Each chunk keeps the maximum contiguous area size hint which is
 * guaranteed to be equal to or larger than the maximum contiguous
 * area in the chunk.  This helps the allocator not to iterate the
 * chunk maps unnecessarily.
 *
 * Allocation state in each chunk is kept using an array of integers
 * on chunk->map.  A positive value in the map represents a free
 * region and negative allocated.  Allocation inside a chunk is done
 * by scanning this map sequentially and serving the first matching
 * entry.  This is mostly copied from the percpu_modalloc() allocator.
 * Chunks can be determined from the address using the index field
 * in the page struct. The index field contains a pointer to the chunk.
 *
 * To use this allocator, arch code should do the followings.
 *
 * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
 *   regular address to percpu pointer and back if they need to be
 *   different from the default
 *
 * - use pcpu_setup_first_chunk() during percpu area initialization to
 *   setup the first chunk containing the kernel static percpu area
 */

#include <linux/bitmap.h>
#include <linux/bootmem.h>
#include <linux/err.h>
#include <linux/list.h>
#include <linux/log2.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/pfn.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
#include <linux/kmemleak.h>

#include <asm/cacheflush.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/io.h>

#define PCPU_SLOT_BASE_SHIFT        5   /* 1-31 shares the same slot */
#define PCPU_DFL_MAP_ALLOC      16  /* start a map with 16 ents */

#ifdef CONFIG_SMP
/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
#ifndef __addr_to_pcpu_ptr
#define __addr_to_pcpu_ptr(addr)                    \
    (void __percpu *)((unsigned long)(addr) -           \
              (unsigned long)pcpu_base_addr +       \
              (unsigned long)__per_cpu_start)
#endif
#ifndef __pcpu_ptr_to_addr
#define __pcpu_ptr_to_addr(ptr)                     \
    (void __force *)((unsigned long)(ptr) +             \
             (unsigned long)pcpu_base_addr -        \
             (unsigned long)__per_cpu_start)
#endif
#else   /* CONFIG_SMP */
/* on UP, it's always identity mapped */
#define __addr_to_pcpu_ptr(addr)    (void __percpu *)(addr)
#define __pcpu_ptr_to_addr(ptr)     (void __force *)(ptr)
#endif  /* CONFIG_SMP */

struct pcpu_chunk {
    struct list_head    list;       /* linked to pcpu_slot lists */
    int         free_size;  /* free bytes in the chunk */
    int         contig_hint;    /* max contiguous size hint */
    void            *base_addr; /* base address of this chunk */
    int         map_used;   /* # of map entries used */
    int         map_alloc;  /* # of map entries allocated */
    int         *map;       /* allocation map */
    void            *data;      /* chunk data */
    bool            immutable;  /* no [de]population allowed */
    unsigned long       populated[];    /* populated bitmap */
};

static int pcpu_unit_pages __read_mostly;
static int pcpu_unit_size __read_mostly;
static int pcpu_nr_units __read_mostly;
static int pcpu_atom_size __read_mostly;
static int pcpu_nr_slots __read_mostly;
static size_t pcpu_chunk_struct_size __read_mostly;

/* cpus with the lowest and highest unit addresses */
static unsigned int pcpu_low_unit_cpu __read_mostly;
static unsigned int pcpu_high_unit_cpu __read_mostly;

/* the address of the first chunk which starts with the kernel static area */
void *pcpu_base_addr __read_mostly;
EXPORT_SYMBOL_GPL(pcpu_base_addr);

static const int *pcpu_unit_map __read_mostly;      /* cpu -> unit */
const unsigned long *pcpu_unit_offsets __read_mostly;   /* cpu -> unit offset */

/* group information, used for vm allocation */
static int pcpu_nr_groups __read_mostly;
static const unsigned long *pcpu_group_offsets __read_mostly;
static const size_t *pcpu_group_sizes __read_mostly;

/*
 * The first chunk which always exists.  Note that unlike other
 * chunks, this one can be allocated and mapped in several different
 * ways and thus often doesn't live in the vmalloc area.
 */
static struct pcpu_chunk *pcpu_first_chunk;

/*
 * Optional reserved chunk.  This chunk reserves part of the first
 * chunk and serves it for reserved allocations.  The amount of
 * reserved offset is in pcpu_reserved_chunk_limit.  When reserved
 * area doesn't exist, the following variables contain NULL and 0
 * respectively.
 */
static struct pcpu_chunk *pcpu_reserved_chunk;
static int pcpu_reserved_chunk_limit;

/*
 * Synchronization rules.
 *
 * There are two locks - pcpu_alloc_mutex and pcpu_lock.  The former
 * protects allocation/reclaim paths, chunks, populated bitmap and
 * vmalloc mapping.  The latter is a spinlock and protects the index
 * data structures - chunk slots, chunks and area maps in chunks.
 *
 * During allocation, pcpu_alloc_mutex is kept locked all the time and
 * pcpu_lock is grabbed and released as necessary.  All actual memory
 * allocations are done using GFP_KERNEL with pcpu_lock released.  In
 * general, percpu memory can't be allocated with irq off but
 * irqsave/restore are still used in alloc path so that it can be used
 * from early init path - sched_init() specifically.
 *
 * Free path accesses and alters only the index data structures, so it
 * can be safely called from atomic context.  When memory needs to be
 * returned to the system, free path schedules reclaim_work which
 * grabs both pcpu_alloc_mutex and pcpu_lock, unlinks chunks to be
 * reclaimed, release both locks and frees the chunks.  Note that it's
 * necessary to grab both locks to remove a chunk from circulation as
 * allocation path might be referencing the chunk with only
 * pcpu_alloc_mutex locked.
 */
static DEFINE_MUTEX(pcpu_alloc_mutex);  /* protects whole alloc and reclaim */
static DEFINE_SPINLOCK(pcpu_lock);  /* protects index data structures */

static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */

/* reclaim work to release fully free chunks, scheduled from free path */
static void pcpu_reclaim(struct work_struct *work);
static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim);

static bool pcpu_addr_in_first_chunk(void *addr)
{
    void *first_start = pcpu_first_chunk->base_addr;

    return addr >= first_start && addr < first_start + pcpu_unit_size;
}

static bool pcpu_addr_in_reserved_chunk(void *addr)
{
    void *first_start = pcpu_first_chunk->base_addr;

    return addr >= first_start &&
        addr < first_start + pcpu_reserved_chunk_limit;
}

static int __pcpu_size_to_slot(int size)
{
    int highbit = fls(size);    /* size is in bytes */
    return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1);
}

static int pcpu_size_to_slot(int size)
{
    if (size == pcpu_unit_size)
        return pcpu_nr_slots - 1;
    return __pcpu_size_to_slot(size);
}

static int pcpu_chunk_slot(const struct pcpu_chunk *chunk)
{
    if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int))
        return 0;

    return pcpu_size_to_slot(chunk->free_size);
}

/* set the pointer to a chunk in a page struct */
static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
{
    page->index = (unsigned long)pcpu;
}

/* obtain pointer to a chunk from a page struct */
static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
{
    return (struct pcpu_chunk *)page->index;
}

static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx)
{
    return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx;
}

static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
                     unsigned int cpu, int page_idx)
{
    return (unsigned long)chunk->base_addr + pcpu_unit_offsets[cpu] +
        (page_idx << PAGE_SHIFT);
}

static void __maybe_unused pcpu_next_unpop(struct pcpu_chunk *chunk,
                       int *rs, int *re, int end)
{
    *rs = find_next_zero_bit(chunk->populated, end, *rs);
    *re = find_next_bit(chunk->populated, end, *rs + 1);
}

static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
                     int *rs, int *re, int end)
{
    *rs = find_next_bit(chunk->populated, end, *rs);
    *re = find_next_zero_bit(chunk->populated, end, *rs + 1);
}

/*
 * (Un)populated page region iterators.  Iterate over (un)populated
 * page regions between @start and @end in @chunk.  @rs and @re should
 * be integer variables and will be set to start and end page index of
 * the current region.
 */
#define pcpu_for_each_unpop_region(chunk, rs, re, start, end)           \
    for ((rs) = (start), pcpu_next_unpop((chunk), &(rs), &(re), (end)); \
         (rs) < (re);                           \
         (rs) = (re) + 1, pcpu_next_unpop((chunk), &(rs), &(re), (end)))

#define pcpu_for_each_pop_region(chunk, rs, re, start, end)         \
    for ((rs) = (start), pcpu_next_pop((chunk), &(rs), &(re), (end));   \
         (rs) < (re);                           \
         (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))

static void *pcpu_mem_zalloc(size_t size)
{
    if (WARN_ON_ONCE(!slab_is_available()))
        return NULL;

    if (size <= PAGE_SIZE)
        return kzalloc(size, GFP_KERNEL);
    else
        return vzalloc(size);
}

static void pcpu_mem_free(void *ptr, size_t size)
{
    if (size <= PAGE_SIZE)
        kfree(ptr);
    else
        vfree(ptr);
}

static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
{
    int nslot = pcpu_chunk_slot(chunk);

    if (chunk != pcpu_reserved_chunk && oslot != nslot) {
        if (oslot < nslot)
            list_move(&chunk->list, &pcpu_slot[nslot]);
        else
            list_move_tail(&chunk->list, &pcpu_slot[nslot]);
    }
}

static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
{
    int new_alloc;

    if (chunk->map_alloc >= chunk->map_used + 2)
        return 0;

    new_alloc = PCPU_DFL_MAP_ALLOC;
    while (new_alloc < chunk->map_used + 2)
        new_alloc *= 2;

    return new_alloc;
}

static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
{
    int *old = NULL, *new = NULL;
    size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
    unsigned long flags;

    new = pcpu_mem_zalloc(new_size);
    if (!new)
        return -ENOMEM;

    /* acquire pcpu_lock and switch to new area map */
    spin_lock_irqsave(&pcpu_lock, flags);

    if (new_alloc <= chunk->map_alloc)
        goto out_unlock;

    old_size = chunk->map_alloc * sizeof(chunk->map[0]);
    old = chunk->map;

    memcpy(new, old, old_size);

    chunk->map_alloc = new_alloc;
    chunk->map = new;
    new = NULL;

out_unlock:
    spin_unlock_irqrestore(&pcpu_lock, flags);

    /*
     * pcpu_mem_free() might end up calling vfree() which uses
     * IRQ-unsafe lock and thus can't be called under pcpu_lock.
     */
    pcpu_mem_free(old, old_size);
    pcpu_mem_free(new, new_size);

    return 0;
}

static void pcpu_split_block(struct pcpu_chunk *chunk, int i,
                 int head, int tail)
{
    int nr_extra = !!head + !!tail;

    BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra);

    /* insert new subblocks */
    memmove(&chunk->map[i + nr_extra], &chunk->map[i],
        sizeof(chunk->map[0]) * (chunk->map_used - i));
    chunk->map_used += nr_extra;

    if (head) {
        chunk->map[i + 1] = chunk->map[i] - head;
        chunk->map[i++] = head;
    }
    if (tail) {
        chunk->map[i++] -= tail;
        chunk->map[i] = tail;
    }
}

static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
{
    int oslot = pcpu_chunk_slot(chunk);
    int max_contig = 0;
    int i, off;

    for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) {
        bool is_last = i + 1 == chunk->map_used;
        int head, tail;

        /* extra for alignment requirement */
        head = ALIGN(off, align) - off;
        BUG_ON(i == 0 && head != 0);

        if (chunk->map[i] < 0)
            continue;
        if (chunk->map[i] < head + size) {
            max_contig = max(chunk->map[i], max_contig);
            continue;
        }

        /*
         * If head is small or the previous block is free,
         * merge'em.  Note that 'small' is defined as smaller
         * than sizeof(int), which is very small but isn't too
         * uncommon for percpu allocations.
         */
        if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) {
            if (chunk->map[i - 1] > 0)
                chunk->map[i - 1] += head;
            else {
                chunk->map[i - 1] -= head;
                chunk->free_size -= head;
            }
            chunk->map[i] -= head;
            off += head;
            head = 0;
        }

        /* if tail is small, just keep it around */
        tail = chunk->map[i] - head - size;
        if (tail < sizeof(int))
            tail = 0;

        /* split if warranted */
        if (head || tail) {
            pcpu_split_block(chunk, i, head, tail);
            if (head) {
                i++;
                off += head;
                max_contig = max(chunk->map[i - 1], max_contig);
            }
            if (tail)
                max_contig = max(chunk->map[i + 1], max_contig);
        }

        /* update hint and mark allocated */
        if (is_last)
            chunk->contig_hint = max_contig; /* fully scanned */
        else
            chunk->contig_hint = max(chunk->contig_hint,
                         max_contig);

        chunk->free_size -= chunk->map[i];
        chunk->map[i] = -chunk->map[i];

        pcpu_chunk_relocate(chunk, oslot);
        return off;
    }

    chunk->contig_hint = max_contig;    /* fully scanned */
    pcpu_chunk_relocate(chunk, oslot);

    /* tell the upper layer that this chunk has no matching area */
    return -1;
}

static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
{
    int oslot = pcpu_chunk_slot(chunk);
    int i, off;

    for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++]))
        if (off == freeme)
            break;
    BUG_ON(off != freeme);
    BUG_ON(chunk->map[i] > 0);

    chunk->map[i] = -chunk->map[i];
    chunk->free_size += chunk->map[i];

    /* merge with previous? */
    if (i > 0 && chunk->map[i - 1] >= 0) {
        chunk->map[i - 1] += chunk->map[i];
        chunk->map_used--;
        memmove(&chunk->map[i], &chunk->map[i + 1],
            (chunk->map_used - i) * sizeof(chunk->map[0]));
        i--;
    }
    /* merge with next? */
    if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) {
        chunk->map[i] += chunk->map[i + 1];
        chunk->map_used--;
        memmove(&chunk->map[i + 1], &chunk->map[i + 2],
            (chunk->map_used - (i + 1)) * sizeof(chunk->map[0]));
    }

    chunk->contig_hint = max(chunk->map[i], chunk->contig_hint);
    pcpu_chunk_relocate(chunk, oslot);
}

static struct pcpu_chunk *pcpu_alloc_chunk(void)
{
    struct pcpu_chunk *chunk;

    chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
    if (!chunk)
        return NULL;

    chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
                        sizeof(chunk->map[0]));
    if (!chunk->map) {
        kfree(chunk);
        return NULL;
    }

    chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
    chunk->map[chunk->map_used++] = pcpu_unit_size;

    INIT_LIST_HEAD(&chunk->list);
    chunk->free_size = pcpu_unit_size;
    chunk->contig_hint = pcpu_unit_size;

    return chunk;
}

static void pcpu_free_chunk(struct pcpu_chunk *chunk)
{
    if (!chunk)
        return;
    pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
    kfree(chunk);
}

/*
 * Chunk management implementation.
 *
 * To allow different implementations, chunk alloc/free and
 * [de]population are implemented in a separate file which is pulled
 * into this file and compiled together.  The following functions
 * should be implemented.
 *
 * pcpu_populate_chunk      - populate the specified range of a chunk
 * pcpu_depopulate_chunk    - depopulate the specified range of a chunk
 * pcpu_create_chunk        - create a new chunk
 * pcpu_destroy_chunk       - destroy a chunk, always preceded by full depop
 * pcpu_addr_to_page        - translate address to physical address
 * pcpu_verify_alloc_info   - check alloc_info is acceptable during init
 */
static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size);
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size);
static struct pcpu_chunk *pcpu_create_chunk(void);
static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
static struct page *pcpu_addr_to_page(void *addr);
static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);

#ifdef CONFIG_NEED_PER_CPU_KM
#include "percpu-km.c"
#else
#include "percpu-vm.c"
#endif

static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
    /* is it in the first chunk? */
    if (pcpu_addr_in_first_chunk(addr)) {
        /* is it in the reserved area? */
        if (pcpu_addr_in_reserved_chunk(addr))
            return pcpu_reserved_chunk;
        return pcpu_first_chunk;
    }

    /*
     * The address is relative to unit0 which might be unused and
     * thus unmapped.  Offset the address to the unit space of the
     * current processor before looking it up in the vmalloc
     * space.  Note that any possible cpu id can be used here, so
     * there's no need to worry about preemption or cpu hotplug.
     */
    addr += pcpu_unit_offsets[raw_smp_processor_id()];
    return pcpu_get_page_chunk(pcpu_addr_to_page(addr));
}

static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
{
    static int warn_limit = 10;
    struct pcpu_chunk *chunk;
    const char *err;
    int slot, off, new_alloc;
    unsigned long flags;
    void __percpu *ptr;

    if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
        WARN(true, "illegal size (%zu) or align (%zu) for "
             "percpu allocation\n", size, align);
        return NULL;
    }

    mutex_lock(&pcpu_alloc_mutex);
    spin_lock_irqsave(&pcpu_lock, flags);

    /* serve reserved allocations from the reserved chunk if available */
    if (reserved && pcpu_reserved_chunk) {
        chunk = pcpu_reserved_chunk;

        if (size > chunk->contig_hint) {
            err = "alloc from reserved chunk failed";
            goto fail_unlock;
        }

        while ((new_alloc = pcpu_need_to_extend(chunk))) {
            spin_unlock_irqrestore(&pcpu_lock, flags);
            if (pcpu_extend_area_map(chunk, new_alloc) < 0) {
                err = "failed to extend area map of reserved chunk";
                goto fail_unlock_mutex;
            }
            spin_lock_irqsave(&pcpu_lock, flags);
        }

        off = pcpu_alloc_area(chunk, size, align);
        if (off >= 0)
            goto area_found;

        err = "alloc from reserved chunk failed";
        goto fail_unlock;
    }

restart:
    /* search through normal chunks */
    for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) {
        list_for_each_entry(chunk, &pcpu_slot[slot], list) {
            if (size > chunk->contig_hint)
                continue;

            new_alloc = pcpu_need_to_extend(chunk);
            if (new_alloc) {
                spin_unlock_irqrestore(&pcpu_lock, flags);
                if (pcpu_extend_area_map(chunk,
                             new_alloc) < 0) {
                    err = "failed to extend area map";
                    goto fail_unlock_mutex;
                }
                spin_lock_irqsave(&pcpu_lock, flags);
                /*
                 * pcpu_lock has been dropped, need to
                 * restart cpu_slot list walking.
                 */
                goto restart;
            }

            off = pcpu_alloc_area(chunk, size, align);
            if (off >= 0)
                goto area_found;
        }
    }

    /* hmmm... no space left, create a new chunk */
    spin_unlock_irqrestore(&pcpu_lock, flags);

    chunk = pcpu_create_chunk();
    if (!chunk) {
        err = "failed to allocate new chunk";
        goto fail_unlock_mutex;
    }

    spin_lock_irqsave(&pcpu_lock, flags);
    pcpu_chunk_relocate(chunk, -1);
    goto restart;

area_found:
    spin_unlock_irqrestore(&pcpu_lock, flags);

    /* populate, map and clear the area */
    if (pcpu_populate_chunk(chunk, off, size)) {
        spin_lock_irqsave(&pcpu_lock, flags);
        pcpu_free_area(chunk, off);
        err = "failed to populate";
        goto fail_unlock;
    }

    mutex_unlock(&pcpu_alloc_mutex);

    /* return address relative to base address */
    ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
    kmemleak_alloc_percpu(ptr, size);
    return ptr;

fail_unlock:
    spin_unlock_irqrestore(&pcpu_lock, flags);
fail_unlock_mutex:
    mutex_unlock(&pcpu_alloc_mutex);
    if (warn_limit) {
        pr_warning("PERCPU: allocation failed, size=%zu align=%zu, "
               "%s\n", size, align, err);
        dump_stack();
        if (!--warn_limit)
            pr_info("PERCPU: limit reached, disable warning\n");
    }
    return NULL;
}

void __percpu *__alloc_percpu(size_t size, size_t align)
{
    return pcpu_alloc(size, align, false);
}
EXPORT_SYMBOL_GPL(__alloc_percpu);

void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
{
    return pcpu_alloc(size, align, true);
}

static void pcpu_reclaim(struct work_struct *work)
{
    LIST_HEAD(todo);
    struct list_head *head = &pcpu_slot[pcpu_nr_slots - 1];
    struct pcpu_chunk *chunk, *next;

    mutex_lock(&pcpu_alloc_mutex);
    spin_lock_irq(&pcpu_lock);

    list_for_each_entry_safe(chunk, next, head, list) {
        WARN_ON(chunk->immutable);

        /* spare the first one */
        if (chunk == list_first_entry(head, struct pcpu_chunk, list))
            continue;

        list_move(&chunk->list, &todo);
    }

    spin_unlock_irq(&pcpu_lock);

    list_for_each_entry_safe(chunk, next, &todo, list) {
        pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
        pcpu_destroy_chunk(chunk);
    }

    mutex_unlock(&pcpu_alloc_mutex);
}

void free_percpu(void __percpu *ptr)
{
    void *addr;
    struct pcpu_chunk *chunk;
    unsigned long flags;
    int off;

    if (!ptr)
        return;

    kmemleak_free_percpu(ptr);

    addr = __pcpu_ptr_to_addr(ptr);

    spin_lock_irqsave(&pcpu_lock, flags);

    chunk = pcpu_chunk_addr_search(addr);
    off = addr - chunk->base_addr;

    pcpu_free_area(chunk, off);

    /* if there are more than one fully free chunks, wake up grim reaper */
    if (chunk->free_size == pcpu_unit_size) {
        struct pcpu_chunk *pos;

        list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list)
            if (pos != chunk) {
                schedule_work(&pcpu_reclaim_work);
                break;
            }
    }

    spin_unlock_irqrestore(&pcpu_lock, flags);
}
EXPORT_SYMBOL_GPL(free_percpu);

bool is_kernel_percpu_address(unsigned long addr)
{
#ifdef CONFIG_SMP
    const size_t static_size = __per_cpu_end - __per_cpu_start;
    void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
    unsigned int cpu;

    for_each_possible_cpu(cpu) {
        void *start = per_cpu_ptr(base, cpu);

        if ((void *)addr >= start && (void *)addr < start + static_size)
            return true;
        }
#endif
    /* on UP, can't distinguish from other static vars, always false */
    return false;
}

phys_addr_t per_cpu_ptr_to_phys(void *addr)
{
    void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
    bool in_first_chunk = false;
    unsigned long first_low, first_high;
    unsigned int cpu;

    /*
     * The following test on unit_low/high isn't strictly
     * necessary but will speed up lookups of addresses which
     * aren't in the first chunk.
     */
    first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
    first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
                     pcpu_unit_pages);
    if ((unsigned long)addr >= first_low &&
        (unsigned long)addr < first_high) {
        for_each_possible_cpu(cpu) {
            void *start = per_cpu_ptr(base, cpu);

            if (addr >= start && addr < start + pcpu_unit_size) {
                in_first_chunk = true;
                break;
            }
        }
    }

    if (in_first_chunk) {
        if (!is_vmalloc_addr(addr))
            return __pa(addr);
        else
            return page_to_phys(vmalloc_to_page(addr)) +
                   offset_in_page(addr);
    } else
        return page_to_phys(pcpu_addr_to_page(addr)) +
               offset_in_page(addr);
}

struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
                              int nr_units)
{
    struct pcpu_alloc_info *ai;
    size_t base_size, ai_size;
    void *ptr;
    int unit;

    base_size = ALIGN(sizeof(*ai) + nr_groups * sizeof(ai->groups[0]),
              __alignof__(ai->groups[0].cpu_map[0]));
    ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]);

    ptr = alloc_bootmem_nopanic(PFN_ALIGN(ai_size));
    if (!ptr)
        return NULL;
    ai = ptr;
    ptr += base_size;

    ai->groups[0].cpu_map = ptr;

    for (unit = 0; unit < nr_units; unit++)
        ai->groups[0].cpu_map[unit] = NR_CPUS;

    ai->nr_groups = nr_groups;
    ai->__ai_size = PFN_ALIGN(ai_size);

    return ai;
}

void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
{
    free_bootmem(__pa(ai), ai->__ai_size);
}

static void pcpu_dump_alloc_info(const char *lvl,
                 const struct pcpu_alloc_info *ai)
{
    int group_width = 1, cpu_width = 1, width;
    char empty_str[] = "--------";
    int alloc = 0, alloc_end = 0;
    int group, v;
    int upa, apl;   /* units per alloc, allocs per line */

    v = ai->nr_groups;
    while (v /= 10)
        group_width++;

    v = num_possible_cpus();
    while (v /= 10)
        cpu_width++;
    empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0';

    upa = ai->alloc_size / ai->unit_size;
    width = upa * (cpu_width + 1) + group_width + 3;
    apl = rounddown_pow_of_two(max(60 / width, 1));

    printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu",
           lvl, ai->static_size, ai->reserved_size, ai->dyn_size,
           ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size);

    for (group = 0; group < ai->nr_groups; group++) {
        const struct pcpu_group_info *gi = &ai->groups[group];
        int unit = 0, unit_end = 0;

        BUG_ON(gi->nr_units % upa);
        for (alloc_end += gi->nr_units / upa;
             alloc < alloc_end; alloc++) {
            if (!(alloc % apl)) {
                printk(KERN_CONT "\n");
                printk("%spcpu-alloc: ", lvl);
            }
            printk(KERN_CONT "[%0*d] ", group_width, group);

            for (unit_end += upa; unit < unit_end; unit++)
                if (gi->cpu_map[unit] != NR_CPUS)
                    printk(KERN_CONT "%0*d ", cpu_width,
                           gi->cpu_map[unit]);
                else
                    printk(KERN_CONT "%s ", empty_str);
        }
    }
    printk(KERN_CONT "\n");
}

int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
                  void *base_addr)
{
    static char cpus_buf[4096] __initdata;
    static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
    static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
    size_t dyn_size = ai->dyn_size;
    size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
    struct pcpu_chunk *schunk, *dchunk = NULL;
    unsigned long *group_offsets;
    size_t *group_sizes;
    unsigned long *unit_off;
    unsigned int cpu;
    int *unit_map;
    int group, unit, i;

    cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask);

#define PCPU_SETUP_BUG_ON(cond) do {                    \
    if (unlikely(cond)) {                       \
        pr_emerg("PERCPU: failed to initialize, %s", #cond);    \
        pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf);   \
        pcpu_dump_alloc_info(KERN_EMERG, ai);           \
        BUG();                          \
    }                               \
} while (0)

    /* sanity checks */
    PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
#ifdef CONFIG_SMP
    PCPU_SETUP_BUG_ON(!ai->static_size);
    PCPU_SETUP_BUG_ON((unsigned long)__per_cpu_start & ~PAGE_MASK);
#endif
    PCPU_SETUP_BUG_ON(!base_addr);
    PCPU_SETUP_BUG_ON((unsigned long)base_addr & ~PAGE_MASK);
    PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
    PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
    PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
    PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
    PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);

    /* process group information and build config tables accordingly */
    group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
    group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0]));
    unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0]));
    unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));

    for (cpu = 0; cpu < nr_cpu_ids; cpu++)
        unit_map[cpu] = UINT_MAX;

    pcpu_low_unit_cpu = NR_CPUS;
    pcpu_high_unit_cpu = NR_CPUS;

    for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
        const struct pcpu_group_info *gi = &ai->groups[group];

        group_offsets[group] = gi->base_offset;
        group_sizes[group] = gi->nr_units * ai->unit_size;

        for (i = 0; i < gi->nr_units; i++) {
            cpu = gi->cpu_map[i];
            if (cpu == NR_CPUS)
                continue;

            PCPU_SETUP_BUG_ON(cpu > nr_cpu_ids);
            PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
            PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX);

            unit_map[cpu] = unit + i;
            unit_off[cpu] = gi->base_offset + i * ai->unit_size;

            /* determine low/high unit_cpu */
            if (pcpu_low_unit_cpu == NR_CPUS ||
                unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
                pcpu_low_unit_cpu = cpu;
            if (pcpu_high_unit_cpu == NR_CPUS ||
                unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
                pcpu_high_unit_cpu = cpu;
        }
    }
    pcpu_nr_units = unit;

    for_each_possible_cpu(cpu)
        PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);

    /* we're done parsing the input, undefine BUG macro and dump config */
#undef PCPU_SETUP_BUG_ON
    pcpu_dump_alloc_info(KERN_DEBUG, ai);

    pcpu_nr_groups = ai->nr_groups;
    pcpu_group_offsets = group_offsets;
    pcpu_group_sizes = group_sizes;
    pcpu_unit_map = unit_map;
    pcpu_unit_offsets = unit_off;

    /* determine basic parameters */
    pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
    pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
    pcpu_atom_size = ai->atom_size;
    pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
        BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);

    /*
     * Allocate chunk slots.  The additional last slot is for
     * empty chunks.
     */
    pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
    pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
    for (i = 0; i < pcpu_nr_slots; i++)
        INIT_LIST_HEAD(&pcpu_slot[i]);

    /*
     * Initialize static chunk.  If reserved_size is zero, the
     * static chunk covers static area + dynamic allocation area
     * in the first chunk.  If reserved_size is not zero, it
     * covers static area + reserved area (mostly used for module
     * static percpu allocation).
     */
    schunk = alloc_bootmem(pcpu_chunk_struct_size);
    INIT_LIST_HEAD(&schunk->list);
    schunk->base_addr = base_addr;
    schunk->map = smap;
    schunk->map_alloc = ARRAY_SIZE(smap);
    schunk->immutable = true;
    bitmap_fill(schunk->populated, pcpu_unit_pages);

    if (ai->reserved_size) {
        schunk->free_size = ai->reserved_size;
        pcpu_reserved_chunk = schunk;
        pcpu_reserved_chunk_limit = ai->static_size + ai->reserved_size;
    } else {
        schunk->free_size = dyn_size;
        dyn_size = 0;           /* dynamic area covered */
    }
    schunk->contig_hint = schunk->free_size;

    schunk->map[schunk->map_used++] = -ai->static_size;
    if (schunk->free_size)
        schunk->map[schunk->map_used++] = schunk->free_size;

    /* init dynamic chunk if necessary */
    if (dyn_size) {
        dchunk = alloc_bootmem(pcpu_chunk_struct_size);
        INIT_LIST_HEAD(&dchunk->list);
        dchunk->base_addr = base_addr;
        dchunk->map = dmap;
        dchunk->map_alloc = ARRAY_SIZE(dmap);
        dchunk->immutable = true;
        bitmap_fill(dchunk->populated, pcpu_unit_pages);

        dchunk->contig_hint = dchunk->free_size = dyn_size;
        dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
        dchunk->map[dchunk->map_used++] = dchunk->free_size;
    }

    /* link the first chunk in */
    pcpu_first_chunk = dchunk ?: schunk;
    pcpu_chunk_relocate(pcpu_first_chunk, -1);

    /* we're done */
    pcpu_base_addr = base_addr;
    return 0;
}

#ifdef CONFIG_SMP

const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = {
    [PCPU_FC_AUTO]  = "auto",
    [PCPU_FC_EMBED] = "embed",
    [PCPU_FC_PAGE]  = "page",
};

enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;

static int __init percpu_alloc_setup(char *str)
{
    if (0)
        /* nada */;
#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
    else if (!strcmp(str, "embed"))
        pcpu_chosen_fc = PCPU_FC_EMBED;
#endif
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
    else if (!strcmp(str, "page"))
        pcpu_chosen_fc = PCPU_FC_PAGE;
#endif
    else
        pr_warning("PERCPU: unknown allocator %s specified\n", str);

    return 0;
}
early_param("percpu_alloc", percpu_alloc_setup);

/*
 * pcpu_embed_first_chunk() is used by the generic percpu setup.
 * Build it if needed by the arch config or the generic setup is going
 * to be used.
 */
#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
    !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
#define BUILD_EMBED_FIRST_CHUNK
#endif

/* build pcpu_page_first_chunk() iff needed by the arch config */
#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
#define BUILD_PAGE_FIRST_CHUNK
#endif

/* pcpu_build_alloc_info() is used by both embed and page first chunk */
#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)

static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
                size_t reserved_size, size_t dyn_size,
                size_t atom_size,
                pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
{
    static int group_map[NR_CPUS] __initdata;
    static int group_cnt[NR_CPUS] __initdata;
    const size_t static_size = __per_cpu_end - __per_cpu_start;
    int nr_groups = 1, nr_units = 0;
    size_t size_sum, min_unit_size, alloc_size;
    int upa, max_upa, uninitialized_var(best_upa);  /* units_per_alloc */
    int last_allocs, group, unit;
    unsigned int cpu, tcpu;
    struct pcpu_alloc_info *ai;
    unsigned int *cpu_map;

    /* this function may be called multiple times */
    memset(group_map, 0, sizeof(group_map));
    memset(group_cnt, 0, sizeof(group_cnt));

    /* calculate size_sum and ensure dyn_size is enough for early alloc */
    size_sum = PFN_ALIGN(static_size + reserved_size +
                max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
    dyn_size = size_sum - static_size - reserved_size;

    /*
     * Determine min_unit_size, alloc_size and max_upa such that
     * alloc_size is multiple of atom_size and is the smallest
     * which can accommodate 4k aligned segments which are equal to
     * or larger than min_unit_size.
     */
    min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);

    alloc_size = roundup(min_unit_size, atom_size);
    upa = alloc_size / min_unit_size;
    while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
        upa--;
    max_upa = upa;

    /* group cpus according to their proximity */
    for_each_possible_cpu(cpu) {
        group = 0;
    next_group:
        for_each_possible_cpu(tcpu) {
            if (cpu == tcpu)
                break;
            if (group_map[tcpu] == group && cpu_distance_fn &&
                (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
                 cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
                group++;
                nr_groups = max(nr_groups, group + 1);
                goto next_group;
            }
        }
        group_map[cpu] = group;
        group_cnt[group]++;
    }

    /*
     * Expand unit size until address space usage goes over 75%
     * and then as much as possible without using more address
     * space.
     */
    last_allocs = INT_MAX;
    for (upa = max_upa; upa; upa--) {
        int allocs = 0, wasted = 0;

        if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
            continue;

        for (group = 0; group < nr_groups; group++) {
            int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
            allocs += this_allocs;
            wasted += this_allocs * upa - group_cnt[group];
        }

        /*
         * Don't accept if wastage is over 1/3.  The
         * greater-than comparison ensures upa==1 always
         * passes the following check.
         */
        if (wasted > num_possible_cpus() / 3)
            continue;

        /* and then don't consume more memory */
        if (allocs > last_allocs)
            break;
        last_allocs = allocs;
        best_upa = upa;
    }
    upa = best_upa;

    /* allocate and fill alloc_info */
    for (group = 0; group < nr_groups; group++)
        nr_units += roundup(group_cnt[group], upa);

    ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
    if (!ai)
        return ERR_PTR(-ENOMEM);
    cpu_map = ai->groups[0].cpu_map;

    for (group = 0; group < nr_groups; group++) {
        ai->groups[group].cpu_map = cpu_map;
        cpu_map += roundup(group_cnt[group], upa);
    }

    ai->static_size = static_size;
    ai->reserved_size = reserved_size;
    ai->dyn_size = dyn_size;
    ai->unit_size = alloc_size / upa;
    ai->atom_size = atom_size;
    ai->alloc_size = alloc_size;

    for (group = 0, unit = 0; group_cnt[group]; group++) {
        struct pcpu_group_info *gi = &ai->groups[group];

        /*
         * Initialize base_offset as if all groups are located
         * back-to-back.  The caller should update this to
         * reflect actual allocation.
         */
        gi->base_offset = unit * ai->unit_size;

        for_each_possible_cpu(cpu)
            if (group_map[cpu] == group)
                gi->cpu_map[gi->nr_units++] = cpu;
        gi->nr_units = roundup(gi->nr_units, upa);
        unit += gi->nr_units;
    }
    BUG_ON(unit != nr_units);

    return ai;
}
#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */

#if defined(BUILD_EMBED_FIRST_CHUNK)

int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
                  size_t atom_size,
                  pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
                  pcpu_fc_alloc_fn_t alloc_fn,
                  pcpu_fc_free_fn_t free_fn)
{
    void *base = (void *)ULONG_MAX;
    void **areas = NULL;
    struct pcpu_alloc_info *ai;
    size_t size_sum, areas_size, max_distance;
    int group, i, rc;

    ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
                   cpu_distance_fn);
    if (IS_ERR(ai))
        return PTR_ERR(ai);

    size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
    areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));

    areas = alloc_bootmem_nopanic(areas_size);
    if (!areas) {
        rc = -ENOMEM;
        goto out_free;
    }

    /* allocate, copy and determine base address */
    for (group = 0; group < ai->nr_groups; group++) {
        struct pcpu_group_info *gi = &ai->groups[group];
        unsigned int cpu = NR_CPUS;
        void *ptr;

        for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++)
            cpu = gi->cpu_map[i];
        BUG_ON(cpu == NR_CPUS);

        /* allocate space for the whole group */
        ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size);
        if (!ptr) {
            rc = -ENOMEM;
            goto out_free_areas;
        }
        /* kmemleak tracks the percpu allocations separately */
        kmemleak_free(ptr);
        areas[group] = ptr;

        base = min(ptr, base);
    }

    /*
     * Copy data and free unused parts.  This should happen after all
     * allocations are complete; otherwise, we may end up with
     * overlapping groups.
     */
    for (group = 0; group < ai->nr_groups; group++) {
        struct pcpu_group_info *gi = &ai->groups[group];
        void *ptr = areas[group];

        for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
            if (gi->cpu_map[i] == NR_CPUS) {
                /* unused unit, free whole */
                free_fn(ptr, ai->unit_size);
                continue;
            }
            /* copy and return the unused part */
            memcpy(ptr, __per_cpu_load, ai->static_size);
            free_fn(ptr + size_sum, ai->unit_size - size_sum);
        }
    }

    /* base address is now known, determine group base offsets */
    max_distance = 0;
    for (group = 0; group < ai->nr_groups; group++) {
        ai->groups[group].base_offset = areas[group] - base;
        max_distance = max_t(size_t, max_distance,
                     ai->groups[group].base_offset);
    }
    max_distance += ai->unit_size;

    /* warn if maximum distance is further than 75% of vmalloc space */
    if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
        pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
               "space 0x%lx\n", max_distance,
               (unsigned long)(VMALLOC_END - VMALLOC_START));
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
        /* and fail if we have fallback */
        rc = -EINVAL;
        goto out_free;
#endif
    }

    pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
        PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
        ai->dyn_size, ai->unit_size);

    rc = pcpu_setup_first_chunk(ai, base);
    goto out_free;

out_free_areas:
    for (group = 0; group < ai->nr_groups; group++)
        free_fn(areas[group],
            ai->groups[group].nr_units * ai->unit_size);
out_free:
    pcpu_free_alloc_info(ai);
    if (areas)
        free_bootmem(__pa(areas), areas_size);
    return rc;
}
#endif /* BUILD_EMBED_FIRST_CHUNK */

#ifdef BUILD_PAGE_FIRST_CHUNK

int __init pcpu_page_first_chunk(size_t reserved_size,
                 pcpu_fc_alloc_fn_t alloc_fn,
                 pcpu_fc_free_fn_t free_fn,
                 pcpu_fc_populate_pte_fn_t populate_pte_fn)
{
    static struct vm_struct vm;
    struct pcpu_alloc_info *ai;
    char psize_str[16];
    int unit_pages;
    size_t pages_size;
    struct page **pages;
    int unit, i, j, rc;

    snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10);

    ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL);
    if (IS_ERR(ai))
        return PTR_ERR(ai);
    BUG_ON(ai->nr_groups != 1);
    BUG_ON(ai->groups[0].nr_units != num_possible_cpus());

    unit_pages = ai->unit_size >> PAGE_SHIFT;

    /* unaligned allocations can't be freed, round up to page size */
    pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
                   sizeof(pages[0]));
    pages = alloc_bootmem(pages_size);

    /* allocate pages */
    j = 0;
    for (unit = 0; unit < num_possible_cpus(); unit++)
        for (i = 0; i < unit_pages; i++) {
            unsigned int cpu = ai->groups[0].cpu_map[unit];
            void *ptr;

            ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE);
            if (!ptr) {
                pr_warning("PERCPU: failed to allocate %s page "
                       "for cpu%u\n", psize_str, cpu);
                goto enomem;
            }
            /* kmemleak tracks the percpu allocations separately */
            kmemleak_free(ptr);
            pages[j++] = virt_to_page(ptr);
        }

    /* allocate vm area, map the pages and copy static data */
    vm.flags = VM_ALLOC;
    vm.size = num_possible_cpus() * ai->unit_size;
    vm_area_register_early(&vm, PAGE_SIZE);

    for (unit = 0; unit < num_possible_cpus(); unit++) {
        unsigned long unit_addr =
            (unsigned long)vm.addr + unit * ai->unit_size;

        for (i = 0; i < unit_pages; i++)
            populate_pte_fn(unit_addr + (i << PAGE_SHIFT));

        /* pte already populated, the following shouldn't fail */
        rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages],
                      unit_pages);
        if (rc < 0)
            panic("failed to map percpu area, err=%d\n", rc);

        /*
         * FIXME: Archs with virtual cache should flush local
         * cache for the linear mapping here - something
         * equivalent to flush_cache_vmap() on the local cpu.
         * flush_cache_vmap() can't be used as most supporting
         * data structures are not set up yet.
         */

        /* copy static data */
        memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
    }

    /* we're ready, commit */
    pr_info("PERCPU: %d %s pages/cpu @%p s%zu r%zu d%zu\n",
        unit_pages, psize_str, vm.addr, ai->static_size,
        ai->reserved_size, ai->dyn_size);

    rc = pcpu_setup_first_chunk(ai, vm.addr);
    goto out_free_ar;

enomem:
    while (--j >= 0)
        free_fn(page_address(pages[j]), PAGE_SIZE);
    rc = -ENOMEM;
out_free_ar:
    free_bootmem(__pa(pages), pages_size);
    pcpu_free_alloc_info(ai);
    return rc;
}
#endif /* BUILD_PAGE_FIRST_CHUNK */

#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
/*
 * Generic SMP percpu area setup.
 *
 * The embedding helper is used because its behavior closely resembles
 * the original non-dynamic generic percpu area setup.  This is
 * important because many archs have addressing restrictions and might
 * fail if the percpu area is located far away from the previous
 * location.  As an added bonus, in non-NUMA cases, embedding is
 * generally a good idea TLB-wise because percpu area can piggy back
 * on the physical linear memory mapping which uses large page
 * mappings on applicable archs.
 */
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);

static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
                       size_t align)
{
    return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
}

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

void __init setup_per_cpu_areas(void)
{
    unsigned long delta;
    unsigned int cpu;
    int rc;

    /*
     * Always reserve area for module percpu variables.  That's
     * what the legacy allocator did.
     */
    rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
                    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
                    pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
    if (rc < 0)
        panic("Failed to initialize percpu areas.");

    delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
    for_each_possible_cpu(cpu)
        __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
}
#endif  /* CONFIG_HAVE_SETUP_PER_CPU_AREA */

#else   /* CONFIG_SMP */

/*
 * UP percpu area setup.
 *
 * UP always uses km-based percpu allocator with identity mapping.
 * Static percpu variables are indistinguishable from the usual static
 * variables and don't require any special preparation.
 */
void __init setup_per_cpu_areas(void)
{
    const size_t unit_size =
        roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE,
                     PERCPU_DYNAMIC_RESERVE));
    struct pcpu_alloc_info *ai;
    void *fc;

    ai = pcpu_alloc_alloc_info(1, 1);
    fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
    if (!ai || !fc)
        panic("Failed to allocate memory for percpu areas.");
    /* kmemleak tracks the percpu allocations separately */
    kmemleak_free(fc);

    ai->dyn_size = unit_size;
    ai->unit_size = unit_size;
    ai->atom_size = unit_size;
    ai->alloc_size = unit_size;
    ai->groups[0].nr_units = 1;
    ai->groups[0].cpu_map[0] = 0;

    if (pcpu_setup_first_chunk(ai, fc) < 0)
        panic("Failed to initialize percpu areas.");
}

#endif  /* CONFIG_SMP */

/*
 * First and reserved chunks are initialized with temporary allocation
 * map in initdata so that they can be used before slab is online.
 * This function is called after slab is brought up and replaces those
 * with properly allocated maps.
 */
void __init percpu_init_late(void)
{
    struct pcpu_chunk *target_chunks[] =
        { pcpu_first_chunk, pcpu_reserved_chunk, NULL };
    struct pcpu_chunk *chunk;
    unsigned long flags;
    int i;

    for (i = 0; (chunk = target_chunks[i]); i++) {
        int *map;
        const size_t size = PERCPU_DYNAMIC_EARLY_SLOTS * sizeof(map[0]);

        BUILD_BUG_ON(size > PAGE_SIZE);

        map = pcpu_mem_zalloc(size);
        BUG_ON(!map);

        spin_lock_irqsave(&pcpu_lock, flags);
        memcpy(map, chunk->map, size);
        chunk->map = map;
        spin_unlock_irqrestore(&pcpu_lock, flags);
    }
}