Release 4.11 mm/percpu.c
/*
* mm/percpu.c - percpu memory allocator
*
* Copyright (C) 2009 SUSE Linux Products GmbH
* Copyright (C) 2009 Tejun Heo <tj@kernel.org>
*
* 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 following:
*
* - 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
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#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 */
#define PCPU_ATOMIC_MAP_MARGIN_LOW 32
#define PCPU_ATOMIC_MAP_MARGIN_HIGH 64
#define PCPU_EMPTY_POP_PAGES_LOW 2
#define PCPU_EMPTY_POP_PAGES_HIGH 4
#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 before the sentry */
int map_alloc; /* # of map entries allocated */
int *map; /* allocation map */
struct list_head map_extend_list;/* on pcpu_map_extend_chunks */
void *data; /* chunk data */
int first_free; /* no free below this */
bool immutable; /* no [de]population allowed */
int nr_populated; /* # of populated pages */
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;
static DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */
static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */
static struct list_head *pcpu_slot __read_mostly;
/* chunk list slots */
/* chunks which need their map areas extended, protected by pcpu_lock */
static LIST_HEAD(pcpu_map_extend_chunks);
/*
* The number of empty populated pages, protected by pcpu_lock. The
* reserved chunk doesn't contribute to the count.
*/
static int pcpu_nr_empty_pop_pages;
/*
* Balance work is used to populate or destroy chunks asynchronously. We
* try to keep the number of populated free pages between
* PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one
* empty chunk.
*/
static void pcpu_balance_workfn(struct work_struct *work);
static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn);
static bool pcpu_async_enabled __read_mostly;
static bool pcpu_atomic_alloc_failed;
static void pcpu_schedule_balance_work(void)
{
if (pcpu_async_enabled)
schedule_work(&pcpu_balance_work);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 18 | 100.00% | 1 | 100.00% |
| Total | 18 | 100.00% | 1 | 100.00% |
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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 29 | 100.00% | 1 | 100.00% |
| Total | 29 | 100.00% | 1 | 100.00% |
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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 29 | 100.00% | 1 | 100.00% |
| Total | 29 | 100.00% | 1 | 100.00% |
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 30 | 100.00% | 3 | 100.00% |
| Total | 30 | 100.00% | 3 | 100.00% |
static int pcpu_size_to_slot(int size)
{
if (size == pcpu_unit_size)
return pcpu_nr_slots - 1;
return __pcpu_size_to_slot(size);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 26 | 100.00% | 1 | 100.00% |
| Total | 26 | 100.00% | 1 | 100.00% |
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 43 | 100.00% | 1 | 100.00% |
| Total | 43 | 100.00% | 1 | 100.00% |
/* 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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 26 | 100.00% | 1 | 100.00% |
| Total | 26 | 100.00% | 1 | 100.00% |
/* 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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 23 | 100.00% | 1 | 100.00% |
| Total | 23 | 100.00% | 1 | 100.00% |
static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx)
{
return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 24 | 100.00% | 4 | 100.00% |
| Total | 24 | 100.00% | 4 | 100.00% |
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 39 | 100.00% | 3 | 100.00% |
| Total | 39 | 100.00% | 3 | 100.00% |
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 55 | 100.00% | 4 | 100.00% |
| Total | 55 | 100.00% | 4 | 100.00% |
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 55 | 100.00% | 2 | 100.00% |
| Total | 55 | 100.00% | 2 | 100.00% |
/*
* (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)))
/**
* pcpu_mem_zalloc - allocate memory
* @size: bytes to allocate
*
* Allocate @size bytes. If @size is smaller than PAGE_SIZE,
* kzalloc() is used; otherwise, vzalloc() is used. The returned
* memory is always zeroed.
*
* CONTEXT:
* Does GFP_KERNEL allocation.
*
* RETURNS:
* Pointer to the allocated area on success, NULL on failure.
*/
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 40 | 93.02% | 3 | 60.00% |
| Jesper Juhl | 2 | 4.65% | 1 | 20.00% |
| Bob Liu | 1 | 2.33% | 1 | 20.00% |
| Total | 43 | 100.00% | 5 | 100.00% |
/**
* pcpu_mem_free - free memory
* @ptr: memory to free
*
* Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc().
*/
static void pcpu_mem_free(void *ptr)
{
kvfree(ptr);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 14 | 93.33% | 2 | 66.67% |
| Tetsuo Handa | 1 | 6.67% | 1 | 33.33% |
| Total | 15 | 100.00% | 3 | 100.00% |
/**
* pcpu_count_occupied_pages - count the number of pages an area occupies
* @chunk: chunk of interest
* @i: index of the area in question
*
* Count the number of pages chunk's @i'th area occupies. When the area's
* start and/or end address isn't aligned to page boundary, the straddled
* page is included in the count iff the rest of the page is free.
*/
static int pcpu_count_occupied_pages(struct pcpu_chunk *chunk, int i)
{
int off = chunk->map[i] & ~1;
int end = chunk->map[i + 1] & ~1;
if (!PAGE_ALIGNED(off) && i > 0) {
int prev = chunk->map[i - 1];
if (!(prev & 1) && prev <= round_down(off, PAGE_SIZE))
off = round_down(off, PAGE_SIZE);
}
if (!PAGE_ALIGNED(end) && i + 1 < chunk->map_used) {
int next = chunk->map[i + 1];
int nend = chunk->map[i + 2] & ~1;
if (!(next & 1) && nend >= round_up(end, PAGE_SIZE))
end = round_up(end, PAGE_SIZE);
}
return max_t(int, PFN_DOWN(end) - PFN_UP(off), 0);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 185 | 100.00% | 1 | 100.00% |
| Total | 185 | 100.00% | 1 | 100.00% |
/**
* pcpu_chunk_relocate - put chunk in the appropriate chunk slot
* @chunk: chunk of interest
* @oslot: the previous slot it was on
*
* This function is called after an allocation or free changed @chunk.
* New slot according to the changed state is determined and @chunk is
* moved to the slot. Note that the reserved chunk is never put on
* chunk slots.
*
* CONTEXT:
* pcpu_lock.
*/
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]);
}
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 69 | 100.00% | 2 | 100.00% |
| Total | 69 | 100.00% | 2 | 100.00% |
/**
* pcpu_need_to_extend - determine whether chunk area map needs to be extended
* @chunk: chunk of interest
* @is_atomic: the allocation context
*
* Determine whether area map of @chunk needs to be extended. If
* @is_atomic, only the amount necessary for a new allocation is
* considered; however, async extension is scheduled if the left amount is
* low. If !@is_atomic, it aims for more empty space. Combined, this
* ensures that the map is likely to have enough available space to
* accomodate atomic allocations which can't extend maps directly.
*
* CONTEXT:
* pcpu_lock.
*
* RETURNS:
* New target map allocation length if extension is necessary, 0
* otherwise.
*/
static int pcpu_need_to_extend(struct pcpu_chunk *chunk, bool is_atomic)
{
int margin, new_alloc;
lockdep_assert_held(&pcpu_lock);
if (is_atomic) {
margin = 3;
if (chunk->map_alloc <
chunk->map_used + PCPU_ATOMIC_MAP_MARGIN_LOW) {
if (list_empty(&chunk->map_extend_list)) {
list_add_tail(&chunk->map_extend_list,
&pcpu_map_extend_chunks);
pcpu_schedule_balance_work();
}
}
} else {
margin = PCPU_ATOMIC_MAP_MARGIN_HIGH;
}
if (chunk->map_alloc >= chunk->map_used + margin)
return 0;
new_alloc = PCPU_DFL_MAP_ALLOC;
while (new_alloc < chunk->map_used + margin)
new_alloc *= 2;
return new_alloc;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 118 | 100.00% | 6 | 100.00% |
| Total | 118 | 100.00% | 6 | 100.00% |
/**
* pcpu_extend_area_map - extend area map of a chunk
* @chunk: chunk of interest
* @new_alloc: new target allocation length of the area map
*
* Extend area map of @chunk to have @new_alloc entries.
*
* CONTEXT:
* Does GFP_KERNEL allocation. Grabs and releases pcpu_lock.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
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;
lockdep_assert_held(&pcpu_alloc_mutex);
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);
pcpu_mem_free(new);
return 0;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 148 | 93.08% | 7 | 70.00% |
| Huang Shijie | 7 | 4.40% | 1 | 10.00% |
| Jiri Kosina | 3 | 1.89% | 1 | 10.00% |
| Bob Liu | 1 | 0.63% | 1 | 10.00% |
| Total | 159 | 100.00% | 10 | 100.00% |
/**
* pcpu_fit_in_area - try to fit the requested allocation in a candidate area
* @chunk: chunk the candidate area belongs to
* @off: the offset to the start of the candidate area
* @this_size: the size of the candidate area
* @size: the size of the target allocation
* @align: the alignment of the target allocation
* @pop_only: only allocate from already populated region
*
* We're trying to allocate @size bytes aligned at @align. @chunk's area
* at @off sized @this_size is a candidate. This function determines
* whether the target allocation fits in the candidate area and returns the
* number of bytes to pad after @off. If the target area doesn't fit, -1
* is returned.
*
* If @pop_only is %true, this function only considers the already
* populated part of the candidate area.
*/
static int pcpu_fit_in_area(struct pcpu_chunk *chunk, int off, int this_size,
int size, int align, bool pop_only)
{
int cand_off = off;
while (true) {
int head = ALIGN(cand_off, align) - off;
int page_start, page_end, rs, re;
if (this_size < head + size)
return -1;
if (!pop_only)
return head;
/*
* If the first unpopulated page is beyond the end of the
* allocation, the whole allocation is populated;
* otherwise, retry from the end of the unpopulated area.
*/
page_start = PFN_DOWN(head + off);
page_end = PFN_UP(head + off + size);
rs = page_start;
pcpu_next_unpop(chunk, &rs, &re, PFN_UP(off + this_size));
if (rs >= page_end)
return head;
cand_off = re * PAGE_SIZE;
}
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 136 | 100.00% | 1 | 100.00% |
| Total | 136 | 100.00% | 1 | 100.00% |
/**
* pcpu_alloc_area - allocate area from a pcpu_chunk
* @chunk: chunk of interest
* @size: wanted size in bytes
* @align: wanted align
* @pop_only: allocate only from the populated area
* @occ_pages_p: out param for the number of pages the area occupies
*
* Try to allocate @size bytes area aligned at @align from @chunk.
* Note that this function only allocates the offset. It doesn't
* populate or map the area.
*
* @chunk->map must have at least two free slots.
*
* CONTEXT:
* pcpu_lock.
*
* RETURNS:
* Allocated offset in @chunk on success, -1 if no matching area is
* found.
*/
static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align,
bool pop_only, int *occ_pages_p)
{
int oslot = pcpu_chunk_slot(chunk);
int max_contig = 0;
int i, off;
bool seen_free = false;
int *p;
for (i = chunk->first_free, p = chunk->map + i; i < chunk->map_used; i++, p++) {
int head, tail;
int this_size;
off = *p;
if (off & 1)
continue;
this_size = (p[1] & ~1) - off;
head = pcpu_fit_in_area(chunk, off, this_size, size, align,
pop_only);
if (head < 0) {
if (!seen_free) {
chunk->first_free = i;
seen_free = true;
}
max_contig = max(this_size, 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) || !(p[-1] & 1))) {
*p = off += head;
if (p[-1] & 1)
chunk->free_size -= head;
else
max_contig = max(*p - p[-1], max_contig);
this_size -= head;
head = 0;
}
/* if tail is small, just keep it around */
tail = this_size - head - size;
if (tail < sizeof(int)) {
tail = 0;
size = this_size - head;
}
/* split if warranted */
if (head || tail) {
int nr_extra = !!head + !!tail;
/* insert new subblocks */
memmove(p + nr_extra + 1, p + 1,
sizeof(chunk->map[0]) * (chunk->map_used - i));
chunk->map_used += nr_extra;
if (head) {
if (!seen_free) {
chunk->first_free = i;
seen_free = true;
}
*++p = off += head;
++i;
max_contig = max(head, max_contig);
}
if (tail) {
p[1] = off + size;
max_contig = max(tail, max_contig);
}
}
if (!seen_free)
chunk->first_free = i + 1;
/* update hint and mark allocated */
if (i + 1 == chunk->map_used)
chunk->contig_hint = max_contig; /* fully scanned */
else
chunk->contig_hint = max(chunk->contig_hint,
max_contig);
chunk->free_size -= size;
*p |= 1;
*occ_pages_p = pcpu_count_occupied_pages(chunk, 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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 273 | 55.49% | 4 | 50.00% |
| Al Viro | 198 | 40.24% | 3 | 37.50% |
| Jianyu Zhan | 21 | 4.27% | 1 | 12.50% |
| Total | 492 | 100.00% | 8 | 100.00% |
/**
* pcpu_free_area - free area to a pcpu_chunk
* @chunk: chunk of interest
* @freeme: offset of area to free
* @occ_pages_p: out param for the number of pages the area occupies
*
* Free area starting from @freeme to @chunk. Note that this function
* only modifies the allocation map. It doesn't depopulate or unmap
* the area.
*
* CONTEXT:
* pcpu_lock.
*/
static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme,
int *occ_pages_p)
{
int oslot = pcpu_chunk_slot(chunk);
int off = 0;
unsigned i, j;
int to_free = 0;
int *p;
freeme |= 1; /* we are searching for <given offset, in use> pair */
i = 0;
j = chunk->map_used;
while (i != j) {
unsigned k = (i + j) / 2;
off = chunk->map[k];
if (off < freeme)
i = k + 1;
else if (off > freeme)
j = k;
else
i = j = k;
}
BUG_ON(off != freeme);
if (i < chunk->first_free)
chunk->first_free = i;
p = chunk->map + i;
*p = off &= ~1;
chunk->free_size += (p[1] & ~1) - off;
*occ_pages_p = pcpu_count_occupied_pages(chunk, i);
/* merge with next? */
if (!(p[1] & 1))
to_free++;
/* merge with previous? */
if (i > 0 && !(p[-1] & 1)) {
to_free++;
i--;
p--;
}
if (to_free) {
chunk->map_used -= to_free;
memmove(p + 1, p + 1 + to_free,
(chunk->map_used - i) * sizeof(chunk->map[0]));
}
chunk->contig_hint = max(chunk->map[i + 1] - chunk->map[i] - 1, chunk->contig_hint);
pcpu_chunk_relocate(chunk, oslot);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Al Viro | 169 | 55.41% | 2 | 33.33% |
| Tejun Heo | 136 | 44.59% | 4 | 66.67% |
| Total | 305 | 100.00% | 6 | 100.00% |
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) {
pcpu_mem_free(chunk);
return NULL;
}
chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
chunk->map[0] = 0;
chunk->map[1] = pcpu_unit_size | 1;
chunk->map_used = 1;
INIT_LIST_HEAD(&chunk->list);
INIT_LIST_HEAD(&chunk->map_extend_list);
chunk->free_size = pcpu_unit_size;
chunk->contig_hint = pcpu_unit_size;
return chunk;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 110 | 85.27% | 6 | 66.67% |
| Al Viro | 16 | 12.40% | 1 | 11.11% |
| Bob Liu | 2 | 1.55% | 1 | 11.11% |
| Jianyu Zhan | 1 | 0.78% | 1 | 11.11% |
| Total | 129 | 100.00% | 9 | 100.00% |
static void pcpu_free_chunk(struct pcpu_chunk *chunk)
{
if (!chunk)
return;
pcpu_mem_free(chunk->map);
pcpu_mem_free(chunk);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 28 | 96.55% | 3 | 75.00% |
| JoonSoo Kim | 1 | 3.45% | 1 | 25.00% |
| Total | 29 | 100.00% | 4 | 100.00% |
/**
* pcpu_chunk_populated - post-population bookkeeping
* @chunk: pcpu_chunk which got populated
* @page_start: the start page
* @page_end: the end page
*
* Pages in [@page_start,@page_end) have been populated to @chunk. Update
* the bookkeeping information accordingly. Must be called after each
* successful population.
*/
static void pcpu_chunk_populated(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
int nr = page_end - page_start;
lockdep_assert_held(&pcpu_lock);
bitmap_set(chunk->populated, page_start, nr);
chunk->nr_populated += nr;
pcpu_nr_empty_pop_pages += nr;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 51 | 100.00% | 1 | 100.00% |
| Total | 51 | 100.00% | 1 | 100.00% |
/**
* pcpu_chunk_depopulated - post-depopulation bookkeeping
* @chunk: pcpu_chunk which got depopulated
* @page_start: the start page
* @page_end: the end page
*
* Pages in [@page_start,@page_end) have been depopulated from @chunk.
* Update the bookkeeping information accordingly. Must be called after
* each successful depopulation.
*/
static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
int nr = page_end - page_start;
lockdep_assert_held(&pcpu_lock);
bitmap_clear(chunk->populated, page_start, nr);
chunk->nr_populated -= nr;
pcpu_nr_empty_pop_pages -= nr;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 51 | 100.00% | 1 | 100.00% |
| Total | 51 | 100.00% | 1 | 100.00% |
/*
* 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
/**
* pcpu_chunk_addr_search - determine chunk containing specified address
* @addr: address for which the chunk needs to be determined.
*
* RETURNS:
* The address of the found chunk.
*/
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));
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 54 | 100.00% | 2 | 100.00% |
| Total | 54 | 100.00% | 2 | 100.00% |
/**
* pcpu_alloc - the percpu allocator
* @size: size of area to allocate in bytes
* @align: alignment of area (max PAGE_SIZE)
* @reserved: allocate from the reserved chunk if available
* @gfp: allocation flags
*
* Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't
* contain %GFP_KERNEL, the allocation is atomic.
*
* RETURNS:
* Percpu pointer to the allocated area on success, NULL on failure.
*/
static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
gfp_t gfp)
{
static int warn_limit = 10;
struct pcpu_chunk *chunk;
const char *err;
bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
int occ_pages = 0;
int slot, off, new_alloc, cpu, ret;
unsigned long flags;
void __percpu *ptr;
/*
* We want the lowest bit of offset available for in-use/free
* indicator, so force >= 16bit alignment and make size even.
*/
if (unlikely(align < 2))
align = 2;
size = ALIGN(size, 2);
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE ||
!is_power_of_2(align))) {
WARN(true, "illegal size (%zu) or align (%zu) for percpu allocation\n",
size, align);
return NULL;
}
if (!is_atomic)
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, is_atomic))) {
spin_unlock_irqrestore(&pcpu_lock, flags);
if (is_atomic ||
pcpu_extend_area_map(chunk, new_alloc) < 0) {
err = "failed to extend area map of reserved chunk";
goto fail;
}
spin_lock_irqsave(&pcpu_lock, flags);
}
off = pcpu_alloc_area(chunk, size, align, is_atomic,
&occ_pages);
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, is_atomic);
if (new_alloc) {
if (is_atomic)
continue;
spin_unlock_irqrestore(&pcpu_lock, flags);
if (pcpu_extend_area_map(chunk,
new_alloc) < 0) {
err = "failed to extend area map";
goto fail;
}
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, is_atomic,
&occ_pages);
if (off >= 0)
goto area_found;
}
}
spin_unlock_irqrestore(&pcpu_lock, flags);
/*
* No space left. Create a new chunk. We don't want multiple
* tasks to create chunks simultaneously. Serialize and create iff
* there's still no empty chunk after grabbing the mutex.
*/
if (is_atomic)
goto fail;
if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
chunk = pcpu_create_chunk();
if (!chunk) {
err = "failed to allocate new chunk";
goto fail;
}
spin_lock_irqsave(&pcpu_lock, flags);
pcpu_chunk_relocate(chunk, -1);
} else {
spin_lock_irqsave(&pcpu_lock, flags);
}
goto restart;
area_found:
spin_unlock_irqrestore(&pcpu_lock, flags);
/* populate if not all pages are already there */
if (!is_atomic) {
int page_start, page_end, rs, re;
page_start = PFN_DOWN(off);
page_end = PFN_UP(off + size);
pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
WARN_ON(chunk->immutable);
ret = pcpu_populate_chunk(chunk, rs, re);
spin_lock_irqsave(&pcpu_lock, flags);
if (ret) {
pcpu_free_area(chunk, off, &occ_pages);
err = "failed to populate";
goto fail_unlock;
}
pcpu_chunk_populated(chunk, rs, re);
spin_unlock_irqrestore(&pcpu_lock, flags);
}
mutex_unlock(&pcpu_alloc_mutex);
}
if (chunk != pcpu_reserved_chunk) {
spin_lock_irqsave(&pcpu_lock, flags);
pcpu_nr_empty_pop_pages -= occ_pages;
spin_unlock_irqrestore(&pcpu_lock, flags);
}
if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
pcpu_schedule_balance_work();
/* clear the areas and return address relative to base address */
for_each_possible_cpu(cpu)
memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
kmemleak_alloc_percpu(ptr, size, gfp);
return ptr;
fail_unlock:
spin_unlock_irqrestore(&pcpu_lock, flags);
fail:
if (!is_atomic && warn_limit) {
pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
size, align, is_atomic, err);
dump_stack();
if (!--warn_limit)
pr_info("limit reached, disable warning\n");
}
if (is_atomic) {
/* see the flag handling in pcpu_blance_workfn() */
pcpu_atomic_alloc_failed = true;
pcpu_schedule_balance_work();
} else {
mutex_unlock(&pcpu_alloc_mutex);
}
return NULL;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 665 | 87.27% | 21 | 65.62% |
| Jiri Kosina | 24 | 3.15% | 1 | 3.12% |
| Al Viro | 21 | 2.76% | 2 | 6.25% |
| Tahsin Erdogan | 18 | 2.36% | 1 | 3.12% |
| Catalin Marinas | 17 | 2.23% | 1 | 3.12% |
| zijun_hu | 6 | 0.79% | 1 | 3.12% |
| Christoph Lameter | 5 | 0.66% | 1 | 3.12% |
| Joe Perches | 4 | 0.52% | 3 | 9.38% |
| Larry Finger | 2 | 0.26% | 1 | 3.12% |
| Total | 762 | 100.00% | 32 | 100.00% |
/**
* __alloc_percpu_gfp - allocate dynamic percpu area
* @size: size of area to allocate in bytes
* @align: alignment of area (max PAGE_SIZE)
* @gfp: allocation flags
*
* Allocate zero-filled percpu area of @size bytes aligned at @align. If
* @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
* be called from any context but is a lot more likely to fail.
*
* RETURNS:
* Percpu pointer to the allocated area on success, NULL on failure.
*/
void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp)
{
return pcpu_alloc(size, align, false, gfp);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 28 | 100.00% | 1 | 100.00% |
| Total | 28 | 100.00% | 1 | 100.00% |
EXPORT_SYMBOL_GPL(__alloc_percpu_gfp);
/**
* __alloc_percpu - allocate dynamic percpu area
* @size: size of area to allocate in bytes
* @align: alignment of area (max PAGE_SIZE)
*
* Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL).
*/
void __percpu *__alloc_percpu(size_t size, size_t align)
{
return pcpu_alloc(size, align, false, GFP_KERNEL);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 25 | 100.00% | 3 | 100.00% |
| Total | 25 | 100.00% | 3 | 100.00% |
EXPORT_SYMBOL_GPL(__alloc_percpu);
/**
* __alloc_reserved_percpu - allocate reserved percpu area
* @size: size of area to allocate in bytes
* @align: alignment of area (max PAGE_SIZE)
*
* Allocate zero-filled percpu area of @size bytes aligned at @align
* from reserved percpu area if arch has set it up; otherwise,
* allocation is served from the same dynamic area. Might sleep.
* Might trigger writeouts.
*
* CONTEXT:
* Does GFP_KERNEL allocation.
*
* RETURNS:
* Percpu pointer to the allocated area on success, NULL on failure.
*/
void __percpu *__alloc_reserved_percpu(size_t size, size_t align)
{
return pcpu_alloc(size, align, true, GFP_KERNEL);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 25 | 100.00% | 3 | 100.00% |
| Total | 25 | 100.00% | 3 | 100.00% |
/**
* pcpu_balance_workfn - manage the amount of free chunks and populated pages
* @work: unused
*
* Reclaim all fully free chunks except for the first one.
*/
static void pcpu_balance_workfn(struct work_struct *work)
{
LIST_HEAD(to_free);
struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
struct pcpu_chunk *chunk, *next;
int slot, nr_to_pop, ret;
/*
* There's no reason to keep around multiple unused chunks and VM
* areas can be scarce. Destroy all free chunks except for one.
*/
mutex_lock(&pcpu_alloc_mutex);
spin_lock_irq(&pcpu_lock);
list_for_each_entry_safe(chunk, next, free_head, list) {
WARN_ON(chunk->immutable);
/* spare the first one */
if (chunk == list_first_entry(free_head, struct pcpu_chunk, list))
continue;
list_del_init(&chunk->map_extend_list);
list_move(&chunk->list, &to_free);
}
spin_unlock_irq(&pcpu_lock);
list_for_each_entry_safe(chunk, next, &to_free, list) {
int rs, re;
pcpu_for_each_pop_region(chunk, rs, re, 0, pcpu_unit_pages) {
pcpu_depopulate_chunk(chunk, rs, re);
spin_lock_irq(&pcpu_lock);
pcpu_chunk_depopulated(chunk, rs, re);
spin_unlock_irq(&pcpu_lock);
}
pcpu_destroy_chunk(chunk);
}
/* service chunks which requested async area map extension */
do {
int new_alloc = 0;
spin_lock_irq(&pcpu_lock);
chunk = list_first_entry_or_null(&pcpu_map_extend_chunks,
struct pcpu_chunk, map_extend_list);
if (chunk) {
list_del_init(&chunk->map_extend_list);
new_alloc = pcpu_need_to_extend(chunk, false);
}
spin_unlock_irq(&pcpu_lock);
if (new_alloc)
pcpu_extend_area_map(chunk, new_alloc);
} while (chunk);
/*
* Ensure there are certain number of free populated pages for
* atomic allocs. Fill up from the most packed so that atomic
* allocs don't increase fragmentation. If atomic allocation
* failed previously, always populate the maximum amount. This
* should prevent atomic allocs larger than PAGE_SIZE from keeping
* failing indefinitely; however, large atomic allocs are not
* something we support properly and can be highly unreliable and
* inefficient.
*/
retry_pop:
if (pcpu_atomic_alloc_failed) {
nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
/* best effort anyway, don't worry about synchronization */
pcpu_atomic_alloc_failed = false;
} else {
nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
pcpu_nr_empty_pop_pages,
0, PCPU_EMPTY_POP_PAGES_HIGH);
}
for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) {
int nr_unpop = 0, rs, re;
if (!nr_to_pop)
break;
spin_lock_irq(&pcpu_lock);
list_for_each_entry(chunk, &pcpu_slot[slot], list) {
nr_unpop = pcpu_unit_pages - chunk->nr_populated;
if (nr_unpop)
break;
}
spin_unlock_irq(&pcpu_lock);
if (!nr_unpop)
continue;
/* @chunk can't go away while pcpu_alloc_mutex is held */
pcpu_for_each_unpop_region(chunk, rs, re, 0, pcpu_unit_pages) {
int nr = min(re - rs, nr_to_pop);
ret = pcpu_populate_chunk(chunk, rs, rs + nr);
if (!ret) {
nr_to_pop -= nr;
spin_lock_irq(&pcpu_lock);
pcpu_chunk_populated(chunk, rs, rs + nr);
spin_unlock_irq(&pcpu_lock);
} else {
nr_to_pop = 0;
}
if (!nr_to_pop)
break;
}
}
if (nr_to_pop) {
/* ran out of chunks to populate, create a new one and retry */
chunk = pcpu_create_chunk();
if (chunk) {
spin_lock_irq(&pcpu_lock);
pcpu_chunk_relocate(chunk, -1);
spin_unlock_irq(&pcpu_lock);
goto retry_pop;
}
}
mutex_unlock(&pcpu_alloc_mutex);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 498 | 100.00% | 12 | 100.00% |
| Total | 498 | 100.00% | 12 | 100.00% |
/**
* free_percpu - free percpu area
* @ptr: pointer to area to free
*
* Free percpu area @ptr.
*
* CONTEXT:
* Can be called from atomic context.
*/
void free_percpu(void __percpu *ptr)
{
void *addr;
struct pcpu_chunk *chunk;
unsigned long flags;
int off, occ_pages;
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, &occ_pages);
if (chunk != pcpu_reserved_chunk)
pcpu_nr_empty_pop_pages += occ_pages;
/* 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) {
pcpu_schedule_balance_work();
break;
}
}
spin_unlock_irqrestore(&pcpu_lock, flags);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 123 | 91.11% | 7 | 77.78% |
| Andrew Morton | 7 | 5.19% | 1 | 11.11% |
| Catalin Marinas | 5 | 3.70% | 1 | 11.11% |
| Total | 135 | 100.00% | 9 | 100.00% |
EXPORT_SYMBOL_GPL(free_percpu);
/**
* is_kernel_percpu_address - test whether address is from static percpu area
* @addr: address to test
*
* Test whether @addr belongs to in-kernel static percpu area. Module
* static percpu areas are not considered. For those, use
* is_module_percpu_address().
*
* RETURNS:
* %true if @addr is from in-kernel static percpu area, %false otherwise.
*/
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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 80 | 100.00% | 2 | 100.00% |
| Total | 80 | 100.00% | 2 | 100.00% |
/**
* per_cpu_ptr_to_phys - convert translated percpu address to physical address
* @addr: the address to be converted to physical address
*
* Given @addr which is dereferenceable address obtained via one of
* percpu access macros, this function translates it into its physical
* address. The caller is responsible for ensuring @addr stays valid
* until this function finishes.
*
* percpu allocator has special setup for the first chunk, which currently
* supports either embedding in linear address space or vmalloc mapping,
* and, from the second one, the backing allocator (currently either vm or
* km) provides translation.
*
* The addr can be translated simply without checking if it falls into the
* first chunk. But the current code reflects better how percpu allocator
* actually works, and the verification can discover both bugs in percpu
* allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
* code.
*
* RETURNS:
* The physical address for @addr.
*/
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);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 120 | 73.62% | 4 | 57.14% |
| Vivek Goyal | 29 | 17.79% | 1 | 14.29% |
| Eugene Surovegin | 10 | 6.13% | 1 | 14.29% |
| David Howells | 4 | 2.45% | 1 | 14.29% |
| Total | 163 | 100.00% | 7 | 100.00% |
/**
* pcpu_alloc_alloc_info - allocate percpu allocation info
* @nr_groups: the number of groups
* @nr_units: the number of units
*
* Allocate ai which is large enough for @nr_groups groups containing
* @nr_units units. The returned ai's groups[0].cpu_map points to the
* cpu_map array which is long enough for @nr_units and filled with
* NR_CPUS. It's the caller's responsibility to initialize cpu_map
* pointer of other groups.
*
* RETURNS:
* Pointer to the allocated pcpu_alloc_info on success, NULL on
* failure.
*/
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 = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0);
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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 171 | 98.28% | 2 | 66.67% |
| Santosh Shilimkar | 3 | 1.72% | 1 | 33.33% |
| Total | 174 | 100.00% | 3 | 100.00% |
/**
* pcpu_free_alloc_info - free percpu allocation info
* @ai: pcpu_alloc_info to free
*
* Free @ai which was allocated by pcpu_alloc_alloc_info().
*/
void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
{
memblock_free_early(__pa(ai), ai->__ai_size);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 22 | 95.65% | 1 | 50.00% |
| Santosh Shilimkar | 1 | 4.35% | 1 | 50.00% |
| Total | 23 | 100.00% | 2 | 100.00% |
/**
* pcpu_dump_alloc_info - print out information about pcpu_alloc_info
* @lvl: loglevel
* @ai: allocation info to dump
*
* Print out information about @ai using loglevel @lvl.
*/
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)) {
pr_cont("\n");
printk("%spcpu-alloc: ", lvl);
}
pr_cont("[%0*d] ", group_width, group);
for (unit_end += upa; unit < unit_end; unit++)
if (gi->cpu_map[unit] != NR_CPUS)
pr_cont("%0*d ",
cpu_width, gi->cpu_map[unit]);
else
pr_cont("%s ", empty_str);
}
}
pr_cont("\n");
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 321 | 98.47% | 10 | 90.91% |
| Joe Perches | 5 | 1.53% | 1 | 9.09% |
| Total | 326 | 100.00% | 11 | 100.00% |
/**
* pcpu_setup_first_chunk - initialize the first percpu chunk
* @ai: pcpu_alloc_info describing how to percpu area is shaped
* @base_addr: mapped address
*
* Initialize the first percpu chunk which contains the kernel static
* perpcu area. This function is to be called from arch percpu area
* setup path.
*
* @ai contains all information necessary to initialize the first
* chunk and prime the dynamic percpu allocator.
*
* @ai->static_size is the size of static percpu area.
*
* @ai->reserved_size, if non-zero, specifies the amount of bytes to
* reserve after the static area in the first chunk. This reserves
* the first chunk such that it's available only through reserved
* percpu allocation. This is primarily used to serve module percpu
* static areas on architectures where the addressing model has
* limited offset range for symbol relocations to guarantee module
* percpu symbols fall inside the relocatable range.
*
* @ai->dyn_size determines the number of bytes available for dynamic
* allocation in the first chunk. The area between @ai->static_size +
* @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused.
*
* @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE
* and equal to or larger than @ai->static_size + @ai->reserved_size +
* @ai->dyn_size.
*
* @ai->atom_size is the allocation atom size and used as alignment
* for vm areas.
*
* @ai->alloc_size is the allocation size and always multiple of
* @ai->atom_size. This is larger than @ai->atom_size if
* @ai->unit_size is larger than @ai->atom_size.
*
* @ai->nr_groups and @ai->groups describe virtual memory layout of
* percpu areas. Units which should be colocated are put into the
* same group. Dynamic VM areas will be allocated according to these
* groupings. If @ai->nr_groups is zero, a single group containing
* all units is assumed.
*
* The caller should have mapped the first chunk at @base_addr and
* copied static data to each unit.
*
* If the first chunk ends up with both reserved and dynamic areas, it
* is served by two chunks - one to serve the core static and reserved
* areas and the other for the dynamic area. They share the same vm
* and page map but uses different area allocation map to stay away
* from each other. The latter chunk is circulated in the chunk slots
* and available for dynamic allocation like any other chunks.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
void *base_addr)
{
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;
#define PCPU_SETUP_BUG_ON(cond) do { \
if (unlikely(cond)) { \
pr_emerg("failed to initialize, %s\n", #cond); \
pr_emerg("cpu_possible_mask=%*pb\n", \
cpumask_pr_args(cpu_possible_mask)); \
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(offset_in_page(__per_cpu_start));
#endif
PCPU_SETUP_BUG_ON(!base_addr);
PCPU_SETUP_BUG_ON(offset_in_page(base_addr));
PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size));
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 = memblock_virt_alloc(ai->nr_groups *
sizeof(group_offsets[0]), 0);
group_sizes = memblock_virt_alloc(ai->nr_groups *
sizeof(group_sizes[0]), 0);
unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0);
unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 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 = memblock_virt_alloc(
pcpu_nr_slots * sizeof(pcpu_slot[0]), 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 = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
INIT_LIST_HEAD(&schunk->list);
INIT_LIST_HEAD(&schunk->map_extend_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);
schunk->nr_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[0] = 1;
schunk->map[1] = ai->static_size;
schunk->map_used = 1;
if (schunk->free_size)
schunk->map[++schunk->map_used] = ai->static_size + schunk->free_size;
schunk->map[schunk->map_used] |= 1;
/* init dynamic chunk if necessary */
if (dyn_size) {
dchunk = memblock_virt_alloc(pcpu_chunk_struct_size, 0);
INIT_LIST_HEAD(&dchunk->list);
INIT_LIST_HEAD(&dchunk->map_extend_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->nr_populated = pcpu_unit_pages;
dchunk->contig_hint = dchunk->free_size = dyn_size;
dchunk->map[0] = 1;
dchunk->map[1] = pcpu_reserved_chunk_limit;
dchunk->map[2] = (pcpu_reserved_chunk_limit + dchunk->free_size) | 1;
dchunk->map_used = 2;
}
/* link the first chunk in */
pcpu_first_chunk = dchunk ?: schunk;
pcpu_nr_empty_pop_pages +=
pcpu_count_occupied_pages(pcpu_first_chunk, 1);
pcpu_chunk_relocate(pcpu_first_chunk, -1);
/* we're done */
pcpu_base_addr = base_addr;
return 0;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 872 | 91.31% | 21 | 77.78% |
| Al Viro | 48 | 5.03% | 1 | 3.70% |
| Santosh Shilimkar | 21 | 2.20% | 1 | 3.70% |
| Alexander Kuleshov | 9 | 0.94% | 1 | 3.70% |
| Baoquan He | 3 | 0.31% | 1 | 3.70% |
| Joe Perches | 1 | 0.10% | 1 | 3.70% |
| Dan Carpenter | 1 | 0.10% | 1 | 3.70% |
| Total | 955 | 100.00% | 27 | 100.00% |
#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 (!str)
return -EINVAL;
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_warn("unknown allocator %s specified\n", str);
return 0;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 66 | 85.71% | 3 | 50.00% |
| Cyrill V. Gorcunov | 9 | 11.69% | 1 | 16.67% |
| Joe Perches | 2 | 2.60% | 2 | 33.33% |
| Total | 77 | 100.00% | 6 | 100.00% |
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)
/**
* pcpu_build_alloc_info - build alloc_info considering distances between CPUs
* @reserved_size: the size of reserved percpu area in bytes
* @dyn_size: minimum free size for dynamic allocation in bytes
* @atom_size: allocation atom size
* @cpu_distance_fn: callback to determine distance between cpus, optional
*
* This function determines grouping of units, their mappings to cpus
* and other parameters considering needed percpu size, allocation
* atom size and distances between CPUs.
*
* Groups are always multiples of atom size and CPUs which are of
* LOCAL_DISTANCE both ways are grouped together and share space for
* units in the same group. The returned configuration is guaranteed
* to have CPUs on different nodes on different groups and >=75% usage
* of allocated virtual address space.
*
* RETURNS:
* On success, pointer to the new allocation_info is returned. On
* failure, ERR_PTR value is returned.
*/
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 || (offset_in_page(alloc_size / upa)))
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 || (offset_in_page(alloc_size / upa)))
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;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 627 | 98.90% | 18 | 90.00% |
| Alexander Kuleshov | 6 | 0.95% | 1 | 5.00% |
| Lucas De Marchi | 1 | 0.16% | 1 | 5.00% |
| Total | 634 | 100.00% | 20 | 100.00% |
#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
#if defined(BUILD_EMBED_FIRST_CHUNK)
/**
* pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
* @reserved_size: the size of reserved percpu area in bytes
* @dyn_size: minimum free size for dynamic allocation in bytes
* @atom_size: allocation atom size
* @cpu_distance_fn: callback to determine distance between cpus, optional
* @alloc_fn: function to allocate percpu page
* @free_fn: function to free percpu page
*
* This is a helper to ease setting up embedded first percpu chunk and
* can be called where pcpu_setup_first_chunk() is expected.
*
* If this function is used to setup the first chunk, it is allocated
* by calling @alloc_fn and used as-is without being mapped into
* vmalloc area. Allocations are always whole multiples of @atom_size
* aligned to @atom_size.
*
* This enables the first chunk to piggy back on the linear physical
* mapping which often uses larger page size. Please note that this
* can result in very sparse cpu->unit mapping on NUMA machines thus
* requiring large vmalloc address space. Don't use this allocator if
* vmalloc space is not orders of magnitude larger than distances
* between node memory addresses (ie. 32bit NUMA machines).
*
* @dyn_size specifies the minimum dynamic area size.
*
* If the needed size is smaller than the minimum or specified unit
* size, the leftover is returned using @free_fn.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
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;
unsigned long max_distance;
int group, i, highest_group, 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 = memblock_virt_alloc_nopanic(areas_size, 0);
if (!areas) {
rc = -ENOMEM;
goto out_free;
}
/* allocate, copy and determine base address & max_distance */
highest_group = 0;
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);
if (ptr > areas[highest_group])
highest_group = group;
}
max_distance = areas[highest_group] - base;
max_distance += ai->unit_size * ai->groups[highest_group].nr_units;
/* warn if maximum distance is further than 75% of vmalloc space */
if (max_distance > VMALLOC_TOTAL * 3 / 4) {
pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n",
max_distance, VMALLOC_TOTAL);
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
/* and fail if we have fallback */
rc = -EINVAL;
goto out_free_areas;
#endif
}
/*
* 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 */
for (group = 0; group < ai->nr_groups; group++) {
ai->groups[group].base_offset = areas[group] - base;
}
pr_info("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++)
if (areas[group])
free_fn(areas[group],
ai->groups[group].nr_units * ai->unit_size);
out_free:
pcpu_free_alloc_info(ai);
if (areas)
memblock_free_early(__pa(areas), areas_size);
return rc;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 505 | 83.33% | 21 | 77.78% |
| zijun_hu | 83 | 13.70% | 2 | 7.41% |
| Michael Holzheu | 7 | 1.16% | 1 | 3.70% |
| Catalin Marinas | 6 | 0.99% | 1 | 3.70% |
| Santosh Shilimkar | 4 | 0.66% | 1 | 3.70% |
| Joe Perches | 1 | 0.17% | 1 | 3.70% |
| Total | 606 | 100.00% | 27 | 100.00% |
#endif /* BUILD_EMBED_FIRST_CHUNK */
#ifdef BUILD_PAGE_FIRST_CHUNK
/**
* pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
* @reserved_size: the size of reserved percpu area in bytes
* @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE
* @free_fn: function to free percpu page, always called with PAGE_SIZE
* @populate_pte_fn: function to populate pte
*
* This is a helper to ease setting up page-remapped first percpu
* chunk and can be called where pcpu_setup_first_chunk() is expected.
*
* This is the basic allocator. Static percpu area is allocated
* page-by-page into vmalloc area.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
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;
int upa;
int nr_g0_units;
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);
upa = ai->alloc_size/ai->unit_size;
nr_g0_units = roundup(num_possible_cpus(), upa);
if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) {
pcpu_free_alloc_info(ai);
return -EINVAL;
}
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 = memblock_virt_alloc(pages_size, 0);
/* allocate pages */
j = 0;
for (unit = 0; unit < num_possible_cpus(); unit++) {
unsigned int cpu = ai->groups[0].cpu_map[unit];
for (i = 0; i < unit_pages; i++) {
void *ptr;
ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE);
if (!ptr) {
pr_warn("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("%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:
memblock_free_early(__pa(pages), pages_size);
pcpu_free_alloc_info(ai);
return rc;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 448 | 86.15% | 11 | 68.75% |
| zijun_hu | 59 | 11.35% | 1 | 6.25% |
| Catalin Marinas | 6 | 1.15% | 1 | 6.25% |
| Santosh Shilimkar | 4 | 0.77% | 1 | 6.25% |
| Joe Perches | 3 | 0.58% | 2 | 12.50% |
| Total | 520 | 100.00% | 16 | 100.00% |
#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 memblock_virt_alloc_from_nopanic(
size, align, __pa(MAX_DMA_ADDRESS));
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 30 | 96.77% | 3 | 75.00% |
| Santosh Shilimkar | 1 | 3.23% | 1 | 25.00% |
| Total | 31 | 100.00% | 4 | 100.00% |
static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
{
memblock_free_early(__pa(ptr), size);
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 23 | 95.83% | 2 | 66.67% |
| Santosh Shilimkar | 1 | 4.17% | 1 | 33.33% |
| Total | 24 | 100.00% | 3 | 100.00% |
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];
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 78 | 100.00% | 5 | 100.00% |
| Total | 78 | 100.00% | 5 | 100.00% |
#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 = memblock_virt_alloc_from_nopanic(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.");
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 132 | 94.29% | 1 | 25.00% |
| Catalin Marinas | 6 | 4.29% | 1 | 25.00% |
| Honggang Li | 1 | 0.71% | 1 | 25.00% |
| Santosh Shilimkar | 1 | 0.71% | 1 | 25.00% |
| Total | 140 | 100.00% | 4 | 100.00% |
#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);
}
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 124 | 99.20% | 1 | 50.00% |
| Bob Liu | 1 | 0.80% | 1 | 50.00% |
| Total | 125 | 100.00% | 2 | 100.00% |
/*
* Percpu allocator is initialized early during boot when neither slab or
* workqueue is available. Plug async management until everything is up
* and running.
*/
static int __init percpu_enable_async(void)
{
pcpu_async_enabled = true;
return 0;
}
Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 16 | 100.00% | 1 | 100.00% |
| Total | 16 | 100.00% | 1 | 100.00% |
subsys_initcall(percpu_enable_async);
Overall Contributors
| Person | Tokens | Prop | Commits | CommitProp |
| Tejun Heo | 7465 | 89.27% | 75 | 64.66% |
| Al Viro | 457 | 5.47% | 4 | 3.45% |
| zijun_hu | 148 | 1.77% | 4 | 3.45% |
| Catalin Marinas | 43 | 0.51% | 2 | 1.72% |
| Santosh Shilimkar | 36 | 0.43% | 1 | 0.86% |
| Vivek Goyal | 32 | 0.38% | 1 | 0.86% |
| Jiri Kosina | 27 | 0.32% | 1 | 0.86% |
| Joe Perches | 23 | 0.28% | 4 | 3.45% |
| Jianyu Zhan | 22 | 0.26% | 2 | 1.72% |
| Tahsin Erdogan | 18 | 0.22% | 1 | 0.86% |
| Alexander Kuleshov | 15 | 0.18% | 1 | 0.86% |
| Eugene Surovegin | 10 | 0.12% | 1 | 0.86% |
| Cyrill V. Gorcunov | 9 | 0.11% | 1 | 0.86% |
| Michael Holzheu | 7 | 0.08% | 1 | 0.86% |
| Andrew Morton | 7 | 0.08% | 1 | 0.86% |
| Huang Shijie | 7 | 0.08% | 1 | 0.86% |
| Bob Liu | 6 | 0.07% | 1 | 0.86% |
| Christoph Lameter | 5 | 0.06% | 1 | 0.86% |
| David Howells | 4 | 0.05% | 1 | 0.86% |
| Lucas De Marchi | 3 | 0.04% | 1 | 0.86% |
| Baoquan He | 3 | 0.04% | 1 | 0.86% |
| Larry Finger | 2 | 0.02% | 1 | 0.86% |
| Andi Kleen | 2 | 0.02% | 1 | 0.86% |
| Tetsuo Handa | 2 | 0.02% | 1 | 0.86% |
| Jesper Juhl | 2 | 0.02% | 1 | 0.86% |
| Yannick Guerrini | 2 | 0.02% | 1 | 0.86% |
| Dan Carpenter | 1 | 0.01% | 1 | 0.86% |
| Masahiro Yamada | 1 | 0.01% | 1 | 0.86% |
| Uwe Kleine-König | 1 | 0.01% | 1 | 0.86% |
| JoonSoo Kim | 1 | 0.01% | 1 | 0.86% |
| Honggang Li | 1 | 0.01% | 1 | 0.86% |
| Total | 8362 | 100.00% | 116 | 100.00% |
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.