mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
![Vladimir Davydov](/assets/img/avatar_default.png)
`While growing per memcg caches arrays, we jump between memcontrol.c and slab_common.c in a weird way: memcg_alloc_cache_id - memcontrol.c memcg_update_all_caches - slab_common.c memcg_update_cache_size - memcontrol.c There's absolutely no reason why memcg_update_cache_size can't live on the slab's side though. So let's move it there and settle it comfortably amid per-memcg cache allocation functions. Besides, this patch cleans this function up a bit, removing all the useless comments from it, and renames it to memcg_update_cache_params to conform to memcg_alloc/free_cache_params, which we already have in slab_common.c. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Christoph Lameter <cl@linux.com> Cc: Glauber Costa <glommer@gmail.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: David Rientjes <rientjes@google.com> Cc: Pekka Enberg <penberg@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1060 lines
24 KiB
C
1060 lines
24 KiB
C
/*
|
|
* Slab allocator functions that are independent of the allocator strategy
|
|
*
|
|
* (C) 2012 Christoph Lameter <cl@linux.com>
|
|
*/
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/poison.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/memory.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/module.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/page.h>
|
|
#include <linux/memcontrol.h>
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/kmem.h>
|
|
|
|
#include "slab.h"
|
|
|
|
enum slab_state slab_state;
|
|
LIST_HEAD(slab_caches);
|
|
DEFINE_MUTEX(slab_mutex);
|
|
struct kmem_cache *kmem_cache;
|
|
|
|
/*
|
|
* Set of flags that will prevent slab merging
|
|
*/
|
|
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
|
|
SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
|
|
SLAB_FAILSLAB)
|
|
|
|
#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_CACHE_DMA | SLAB_NOTRACK)
|
|
|
|
/*
|
|
* Merge control. If this is set then no merging of slab caches will occur.
|
|
* (Could be removed. This was introduced to pacify the merge skeptics.)
|
|
*/
|
|
static int slab_nomerge;
|
|
|
|
static int __init setup_slab_nomerge(char *str)
|
|
{
|
|
slab_nomerge = 1;
|
|
return 1;
|
|
}
|
|
|
|
#ifdef CONFIG_SLUB
|
|
__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
|
|
#endif
|
|
|
|
__setup("slab_nomerge", setup_slab_nomerge);
|
|
|
|
/*
|
|
* Determine the size of a slab object
|
|
*/
|
|
unsigned int kmem_cache_size(struct kmem_cache *s)
|
|
{
|
|
return s->object_size;
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_size);
|
|
|
|
#ifdef CONFIG_DEBUG_VM
|
|
static int kmem_cache_sanity_check(const char *name, size_t size)
|
|
{
|
|
struct kmem_cache *s = NULL;
|
|
|
|
if (!name || in_interrupt() || size < sizeof(void *) ||
|
|
size > KMALLOC_MAX_SIZE) {
|
|
pr_err("kmem_cache_create(%s) integrity check failed\n", name);
|
|
return -EINVAL;
|
|
}
|
|
|
|
list_for_each_entry(s, &slab_caches, list) {
|
|
char tmp;
|
|
int res;
|
|
|
|
/*
|
|
* This happens when the module gets unloaded and doesn't
|
|
* destroy its slab cache and no-one else reuses the vmalloc
|
|
* area of the module. Print a warning.
|
|
*/
|
|
res = probe_kernel_address(s->name, tmp);
|
|
if (res) {
|
|
pr_err("Slab cache with size %d has lost its name\n",
|
|
s->object_size);
|
|
continue;
|
|
}
|
|
|
|
#if !defined(CONFIG_SLUB)
|
|
if (!strcmp(s->name, name)) {
|
|
pr_err("%s (%s): Cache name already exists.\n",
|
|
__func__, name);
|
|
dump_stack();
|
|
s = NULL;
|
|
return -EINVAL;
|
|
}
|
|
#endif
|
|
}
|
|
|
|
WARN_ON(strchr(name, ' ')); /* It confuses parsers */
|
|
return 0;
|
|
}
|
|
#else
|
|
static inline int kmem_cache_sanity_check(const char *name, size_t size)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
static int memcg_alloc_cache_params(struct mem_cgroup *memcg,
|
|
struct kmem_cache *s, struct kmem_cache *root_cache)
|
|
{
|
|
size_t size;
|
|
|
|
if (!memcg_kmem_enabled())
|
|
return 0;
|
|
|
|
if (!memcg) {
|
|
size = offsetof(struct memcg_cache_params, memcg_caches);
|
|
size += memcg_limited_groups_array_size * sizeof(void *);
|
|
} else
|
|
size = sizeof(struct memcg_cache_params);
|
|
|
|
s->memcg_params = kzalloc(size, GFP_KERNEL);
|
|
if (!s->memcg_params)
|
|
return -ENOMEM;
|
|
|
|
if (memcg) {
|
|
s->memcg_params->memcg = memcg;
|
|
s->memcg_params->root_cache = root_cache;
|
|
} else
|
|
s->memcg_params->is_root_cache = true;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void memcg_free_cache_params(struct kmem_cache *s)
|
|
{
|
|
kfree(s->memcg_params);
|
|
}
|
|
|
|
static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs)
|
|
{
|
|
int size;
|
|
struct memcg_cache_params *new_params, *cur_params;
|
|
|
|
BUG_ON(!is_root_cache(s));
|
|
|
|
size = offsetof(struct memcg_cache_params, memcg_caches);
|
|
size += num_memcgs * sizeof(void *);
|
|
|
|
new_params = kzalloc(size, GFP_KERNEL);
|
|
if (!new_params)
|
|
return -ENOMEM;
|
|
|
|
cur_params = s->memcg_params;
|
|
memcpy(new_params->memcg_caches, cur_params->memcg_caches,
|
|
memcg_limited_groups_array_size * sizeof(void *));
|
|
|
|
new_params->is_root_cache = true;
|
|
|
|
rcu_assign_pointer(s->memcg_params, new_params);
|
|
if (cur_params)
|
|
kfree_rcu(cur_params, rcu_head);
|
|
|
|
return 0;
|
|
}
|
|
|
|
int memcg_update_all_caches(int num_memcgs)
|
|
{
|
|
struct kmem_cache *s;
|
|
int ret = 0;
|
|
mutex_lock(&slab_mutex);
|
|
|
|
list_for_each_entry(s, &slab_caches, list) {
|
|
if (!is_root_cache(s))
|
|
continue;
|
|
|
|
ret = memcg_update_cache_params(s, num_memcgs);
|
|
/*
|
|
* Instead of freeing the memory, we'll just leave the caches
|
|
* up to this point in an updated state.
|
|
*/
|
|
if (ret)
|
|
goto out;
|
|
}
|
|
|
|
memcg_update_array_size(num_memcgs);
|
|
out:
|
|
mutex_unlock(&slab_mutex);
|
|
return ret;
|
|
}
|
|
#else
|
|
static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
|
|
struct kmem_cache *s, struct kmem_cache *root_cache)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void memcg_free_cache_params(struct kmem_cache *s)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
/*
|
|
* Find a mergeable slab cache
|
|
*/
|
|
int slab_unmergeable(struct kmem_cache *s)
|
|
{
|
|
if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
|
|
return 1;
|
|
|
|
if (!is_root_cache(s))
|
|
return 1;
|
|
|
|
if (s->ctor)
|
|
return 1;
|
|
|
|
/*
|
|
* We may have set a slab to be unmergeable during bootstrap.
|
|
*/
|
|
if (s->refcount < 0)
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
struct kmem_cache *find_mergeable(size_t size, size_t align,
|
|
unsigned long flags, const char *name, void (*ctor)(void *))
|
|
{
|
|
struct kmem_cache *s;
|
|
|
|
if (slab_nomerge || (flags & SLAB_NEVER_MERGE))
|
|
return NULL;
|
|
|
|
if (ctor)
|
|
return NULL;
|
|
|
|
size = ALIGN(size, sizeof(void *));
|
|
align = calculate_alignment(flags, align, size);
|
|
size = ALIGN(size, align);
|
|
flags = kmem_cache_flags(size, flags, name, NULL);
|
|
|
|
list_for_each_entry(s, &slab_caches, list) {
|
|
if (slab_unmergeable(s))
|
|
continue;
|
|
|
|
if (size > s->size)
|
|
continue;
|
|
|
|
if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME))
|
|
continue;
|
|
/*
|
|
* Check if alignment is compatible.
|
|
* Courtesy of Adrian Drzewiecki
|
|
*/
|
|
if ((s->size & ~(align - 1)) != s->size)
|
|
continue;
|
|
|
|
if (s->size - size >= sizeof(void *))
|
|
continue;
|
|
|
|
return s;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Figure out what the alignment of the objects will be given a set of
|
|
* flags, a user specified alignment and the size of the objects.
|
|
*/
|
|
unsigned long calculate_alignment(unsigned long flags,
|
|
unsigned long align, unsigned long size)
|
|
{
|
|
/*
|
|
* If the user wants hardware cache aligned objects then follow that
|
|
* suggestion if the object is sufficiently large.
|
|
*
|
|
* The hardware cache alignment cannot override the specified
|
|
* alignment though. If that is greater then use it.
|
|
*/
|
|
if (flags & SLAB_HWCACHE_ALIGN) {
|
|
unsigned long ralign = cache_line_size();
|
|
while (size <= ralign / 2)
|
|
ralign /= 2;
|
|
align = max(align, ralign);
|
|
}
|
|
|
|
if (align < ARCH_SLAB_MINALIGN)
|
|
align = ARCH_SLAB_MINALIGN;
|
|
|
|
return ALIGN(align, sizeof(void *));
|
|
}
|
|
|
|
static struct kmem_cache *
|
|
do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align,
|
|
unsigned long flags, void (*ctor)(void *),
|
|
struct mem_cgroup *memcg, struct kmem_cache *root_cache)
|
|
{
|
|
struct kmem_cache *s;
|
|
int err;
|
|
|
|
err = -ENOMEM;
|
|
s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
|
|
if (!s)
|
|
goto out;
|
|
|
|
s->name = name;
|
|
s->object_size = object_size;
|
|
s->size = size;
|
|
s->align = align;
|
|
s->ctor = ctor;
|
|
|
|
err = memcg_alloc_cache_params(memcg, s, root_cache);
|
|
if (err)
|
|
goto out_free_cache;
|
|
|
|
err = __kmem_cache_create(s, flags);
|
|
if (err)
|
|
goto out_free_cache;
|
|
|
|
s->refcount = 1;
|
|
list_add(&s->list, &slab_caches);
|
|
out:
|
|
if (err)
|
|
return ERR_PTR(err);
|
|
return s;
|
|
|
|
out_free_cache:
|
|
memcg_free_cache_params(s);
|
|
kfree(s);
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* kmem_cache_create - Create a cache.
|
|
* @name: A string which is used in /proc/slabinfo to identify this cache.
|
|
* @size: The size of objects to be created in this cache.
|
|
* @align: The required alignment for the objects.
|
|
* @flags: SLAB flags
|
|
* @ctor: A constructor for the objects.
|
|
*
|
|
* Returns a ptr to the cache on success, NULL on failure.
|
|
* Cannot be called within a interrupt, but can be interrupted.
|
|
* The @ctor is run when new pages are allocated by the cache.
|
|
*
|
|
* The flags are
|
|
*
|
|
* %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
|
|
* to catch references to uninitialised memory.
|
|
*
|
|
* %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
|
|
* for buffer overruns.
|
|
*
|
|
* %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
|
|
* cacheline. This can be beneficial if you're counting cycles as closely
|
|
* as davem.
|
|
*/
|
|
struct kmem_cache *
|
|
kmem_cache_create(const char *name, size_t size, size_t align,
|
|
unsigned long flags, void (*ctor)(void *))
|
|
{
|
|
struct kmem_cache *s;
|
|
char *cache_name;
|
|
int err;
|
|
|
|
get_online_cpus();
|
|
get_online_mems();
|
|
|
|
mutex_lock(&slab_mutex);
|
|
|
|
err = kmem_cache_sanity_check(name, size);
|
|
if (err) {
|
|
s = NULL; /* suppress uninit var warning */
|
|
goto out_unlock;
|
|
}
|
|
|
|
/*
|
|
* Some allocators will constraint the set of valid flags to a subset
|
|
* of all flags. We expect them to define CACHE_CREATE_MASK in this
|
|
* case, and we'll just provide them with a sanitized version of the
|
|
* passed flags.
|
|
*/
|
|
flags &= CACHE_CREATE_MASK;
|
|
|
|
s = __kmem_cache_alias(name, size, align, flags, ctor);
|
|
if (s)
|
|
goto out_unlock;
|
|
|
|
cache_name = kstrdup(name, GFP_KERNEL);
|
|
if (!cache_name) {
|
|
err = -ENOMEM;
|
|
goto out_unlock;
|
|
}
|
|
|
|
s = do_kmem_cache_create(cache_name, size, size,
|
|
calculate_alignment(flags, align, size),
|
|
flags, ctor, NULL, NULL);
|
|
if (IS_ERR(s)) {
|
|
err = PTR_ERR(s);
|
|
kfree(cache_name);
|
|
}
|
|
|
|
out_unlock:
|
|
mutex_unlock(&slab_mutex);
|
|
|
|
put_online_mems();
|
|
put_online_cpus();
|
|
|
|
if (err) {
|
|
if (flags & SLAB_PANIC)
|
|
panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
|
|
name, err);
|
|
else {
|
|
printk(KERN_WARNING "kmem_cache_create(%s) failed with error %d",
|
|
name, err);
|
|
dump_stack();
|
|
}
|
|
return NULL;
|
|
}
|
|
return s;
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_create);
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
/*
|
|
* memcg_create_kmem_cache - Create a cache for a memory cgroup.
|
|
* @memcg: The memory cgroup the new cache is for.
|
|
* @root_cache: The parent of the new cache.
|
|
* @memcg_name: The name of the memory cgroup (used for naming the new cache).
|
|
*
|
|
* This function attempts to create a kmem cache that will serve allocation
|
|
* requests going from @memcg to @root_cache. The new cache inherits properties
|
|
* from its parent.
|
|
*/
|
|
struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
|
|
struct kmem_cache *root_cache,
|
|
const char *memcg_name)
|
|
{
|
|
struct kmem_cache *s = NULL;
|
|
char *cache_name;
|
|
|
|
get_online_cpus();
|
|
get_online_mems();
|
|
|
|
mutex_lock(&slab_mutex);
|
|
|
|
cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
|
|
memcg_cache_id(memcg), memcg_name);
|
|
if (!cache_name)
|
|
goto out_unlock;
|
|
|
|
s = do_kmem_cache_create(cache_name, root_cache->object_size,
|
|
root_cache->size, root_cache->align,
|
|
root_cache->flags, root_cache->ctor,
|
|
memcg, root_cache);
|
|
if (IS_ERR(s)) {
|
|
kfree(cache_name);
|
|
s = NULL;
|
|
}
|
|
|
|
out_unlock:
|
|
mutex_unlock(&slab_mutex);
|
|
|
|
put_online_mems();
|
|
put_online_cpus();
|
|
|
|
return s;
|
|
}
|
|
|
|
static int memcg_cleanup_cache_params(struct kmem_cache *s)
|
|
{
|
|
int rc;
|
|
|
|
if (!s->memcg_params ||
|
|
!s->memcg_params->is_root_cache)
|
|
return 0;
|
|
|
|
mutex_unlock(&slab_mutex);
|
|
rc = __memcg_cleanup_cache_params(s);
|
|
mutex_lock(&slab_mutex);
|
|
|
|
return rc;
|
|
}
|
|
#else
|
|
static int memcg_cleanup_cache_params(struct kmem_cache *s)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
void slab_kmem_cache_release(struct kmem_cache *s)
|
|
{
|
|
kfree(s->name);
|
|
kmem_cache_free(kmem_cache, s);
|
|
}
|
|
|
|
void kmem_cache_destroy(struct kmem_cache *s)
|
|
{
|
|
get_online_cpus();
|
|
get_online_mems();
|
|
|
|
mutex_lock(&slab_mutex);
|
|
|
|
s->refcount--;
|
|
if (s->refcount)
|
|
goto out_unlock;
|
|
|
|
if (memcg_cleanup_cache_params(s) != 0)
|
|
goto out_unlock;
|
|
|
|
if (__kmem_cache_shutdown(s) != 0) {
|
|
printk(KERN_ERR "kmem_cache_destroy %s: "
|
|
"Slab cache still has objects\n", s->name);
|
|
dump_stack();
|
|
goto out_unlock;
|
|
}
|
|
|
|
list_del(&s->list);
|
|
|
|
mutex_unlock(&slab_mutex);
|
|
if (s->flags & SLAB_DESTROY_BY_RCU)
|
|
rcu_barrier();
|
|
|
|
memcg_free_cache_params(s);
|
|
#ifdef SLAB_SUPPORTS_SYSFS
|
|
sysfs_slab_remove(s);
|
|
#else
|
|
slab_kmem_cache_release(s);
|
|
#endif
|
|
goto out;
|
|
|
|
out_unlock:
|
|
mutex_unlock(&slab_mutex);
|
|
out:
|
|
put_online_mems();
|
|
put_online_cpus();
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_destroy);
|
|
|
|
/**
|
|
* kmem_cache_shrink - Shrink a cache.
|
|
* @cachep: The cache to shrink.
|
|
*
|
|
* Releases as many slabs as possible for a cache.
|
|
* To help debugging, a zero exit status indicates all slabs were released.
|
|
*/
|
|
int kmem_cache_shrink(struct kmem_cache *cachep)
|
|
{
|
|
int ret;
|
|
|
|
get_online_cpus();
|
|
get_online_mems();
|
|
ret = __kmem_cache_shrink(cachep);
|
|
put_online_mems();
|
|
put_online_cpus();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(kmem_cache_shrink);
|
|
|
|
int slab_is_available(void)
|
|
{
|
|
return slab_state >= UP;
|
|
}
|
|
|
|
#ifndef CONFIG_SLOB
|
|
/* Create a cache during boot when no slab services are available yet */
|
|
void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
|
|
unsigned long flags)
|
|
{
|
|
int err;
|
|
|
|
s->name = name;
|
|
s->size = s->object_size = size;
|
|
s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
|
|
err = __kmem_cache_create(s, flags);
|
|
|
|
if (err)
|
|
panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
|
|
name, size, err);
|
|
|
|
s->refcount = -1; /* Exempt from merging for now */
|
|
}
|
|
|
|
struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
|
|
unsigned long flags)
|
|
{
|
|
struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
|
|
|
|
if (!s)
|
|
panic("Out of memory when creating slab %s\n", name);
|
|
|
|
create_boot_cache(s, name, size, flags);
|
|
list_add(&s->list, &slab_caches);
|
|
s->refcount = 1;
|
|
return s;
|
|
}
|
|
|
|
struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
|
|
EXPORT_SYMBOL(kmalloc_caches);
|
|
|
|
#ifdef CONFIG_ZONE_DMA
|
|
struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
|
|
EXPORT_SYMBOL(kmalloc_dma_caches);
|
|
#endif
|
|
|
|
/*
|
|
* Conversion table for small slabs sizes / 8 to the index in the
|
|
* kmalloc array. This is necessary for slabs < 192 since we have non power
|
|
* of two cache sizes there. The size of larger slabs can be determined using
|
|
* fls.
|
|
*/
|
|
static s8 size_index[24] = {
|
|
3, /* 8 */
|
|
4, /* 16 */
|
|
5, /* 24 */
|
|
5, /* 32 */
|
|
6, /* 40 */
|
|
6, /* 48 */
|
|
6, /* 56 */
|
|
6, /* 64 */
|
|
1, /* 72 */
|
|
1, /* 80 */
|
|
1, /* 88 */
|
|
1, /* 96 */
|
|
7, /* 104 */
|
|
7, /* 112 */
|
|
7, /* 120 */
|
|
7, /* 128 */
|
|
2, /* 136 */
|
|
2, /* 144 */
|
|
2, /* 152 */
|
|
2, /* 160 */
|
|
2, /* 168 */
|
|
2, /* 176 */
|
|
2, /* 184 */
|
|
2 /* 192 */
|
|
};
|
|
|
|
static inline int size_index_elem(size_t bytes)
|
|
{
|
|
return (bytes - 1) / 8;
|
|
}
|
|
|
|
/*
|
|
* Find the kmem_cache structure that serves a given size of
|
|
* allocation
|
|
*/
|
|
struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
|
|
{
|
|
int index;
|
|
|
|
if (unlikely(size > KMALLOC_MAX_SIZE)) {
|
|
WARN_ON_ONCE(!(flags & __GFP_NOWARN));
|
|
return NULL;
|
|
}
|
|
|
|
if (size <= 192) {
|
|
if (!size)
|
|
return ZERO_SIZE_PTR;
|
|
|
|
index = size_index[size_index_elem(size)];
|
|
} else
|
|
index = fls(size - 1);
|
|
|
|
#ifdef CONFIG_ZONE_DMA
|
|
if (unlikely((flags & GFP_DMA)))
|
|
return kmalloc_dma_caches[index];
|
|
|
|
#endif
|
|
return kmalloc_caches[index];
|
|
}
|
|
|
|
/*
|
|
* Create the kmalloc array. Some of the regular kmalloc arrays
|
|
* may already have been created because they were needed to
|
|
* enable allocations for slab creation.
|
|
*/
|
|
void __init create_kmalloc_caches(unsigned long flags)
|
|
{
|
|
int i;
|
|
|
|
/*
|
|
* Patch up the size_index table if we have strange large alignment
|
|
* requirements for the kmalloc array. This is only the case for
|
|
* MIPS it seems. The standard arches will not generate any code here.
|
|
*
|
|
* Largest permitted alignment is 256 bytes due to the way we
|
|
* handle the index determination for the smaller caches.
|
|
*
|
|
* Make sure that nothing crazy happens if someone starts tinkering
|
|
* around with ARCH_KMALLOC_MINALIGN
|
|
*/
|
|
BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
|
|
(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
|
|
|
|
for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
|
|
int elem = size_index_elem(i);
|
|
|
|
if (elem >= ARRAY_SIZE(size_index))
|
|
break;
|
|
size_index[elem] = KMALLOC_SHIFT_LOW;
|
|
}
|
|
|
|
if (KMALLOC_MIN_SIZE >= 64) {
|
|
/*
|
|
* The 96 byte size cache is not used if the alignment
|
|
* is 64 byte.
|
|
*/
|
|
for (i = 64 + 8; i <= 96; i += 8)
|
|
size_index[size_index_elem(i)] = 7;
|
|
|
|
}
|
|
|
|
if (KMALLOC_MIN_SIZE >= 128) {
|
|
/*
|
|
* The 192 byte sized cache is not used if the alignment
|
|
* is 128 byte. Redirect kmalloc to use the 256 byte cache
|
|
* instead.
|
|
*/
|
|
for (i = 128 + 8; i <= 192; i += 8)
|
|
size_index[size_index_elem(i)] = 8;
|
|
}
|
|
for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
|
|
if (!kmalloc_caches[i]) {
|
|
kmalloc_caches[i] = create_kmalloc_cache(NULL,
|
|
1 << i, flags);
|
|
}
|
|
|
|
/*
|
|
* Caches that are not of the two-to-the-power-of size.
|
|
* These have to be created immediately after the
|
|
* earlier power of two caches
|
|
*/
|
|
if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
|
|
kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
|
|
|
|
if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
|
|
kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
|
|
}
|
|
|
|
/* Kmalloc array is now usable */
|
|
slab_state = UP;
|
|
|
|
for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
|
|
struct kmem_cache *s = kmalloc_caches[i];
|
|
char *n;
|
|
|
|
if (s) {
|
|
n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));
|
|
|
|
BUG_ON(!n);
|
|
s->name = n;
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_ZONE_DMA
|
|
for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
|
|
struct kmem_cache *s = kmalloc_caches[i];
|
|
|
|
if (s) {
|
|
int size = kmalloc_size(i);
|
|
char *n = kasprintf(GFP_NOWAIT,
|
|
"dma-kmalloc-%d", size);
|
|
|
|
BUG_ON(!n);
|
|
kmalloc_dma_caches[i] = create_kmalloc_cache(n,
|
|
size, SLAB_CACHE_DMA | flags);
|
|
}
|
|
}
|
|
#endif
|
|
}
|
|
#endif /* !CONFIG_SLOB */
|
|
|
|
/*
|
|
* To avoid unnecessary overhead, we pass through large allocation requests
|
|
* directly to the page allocator. We use __GFP_COMP, because we will need to
|
|
* know the allocation order to free the pages properly in kfree.
|
|
*/
|
|
void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
|
|
{
|
|
void *ret;
|
|
struct page *page;
|
|
|
|
flags |= __GFP_COMP;
|
|
page = alloc_kmem_pages(flags, order);
|
|
ret = page ? page_address(page) : NULL;
|
|
kmemleak_alloc(ret, size, 1, flags);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(kmalloc_order);
|
|
|
|
#ifdef CONFIG_TRACING
|
|
void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
|
|
{
|
|
void *ret = kmalloc_order(size, flags, order);
|
|
trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(kmalloc_order_trace);
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLABINFO
|
|
|
|
#ifdef CONFIG_SLAB
|
|
#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
|
|
#else
|
|
#define SLABINFO_RIGHTS S_IRUSR
|
|
#endif
|
|
|
|
void print_slabinfo_header(struct seq_file *m)
|
|
{
|
|
/*
|
|
* Output format version, so at least we can change it
|
|
* without _too_ many complaints.
|
|
*/
|
|
#ifdef CONFIG_DEBUG_SLAB
|
|
seq_puts(m, "slabinfo - version: 2.1 (statistics)\n");
|
|
#else
|
|
seq_puts(m, "slabinfo - version: 2.1\n");
|
|
#endif
|
|
seq_puts(m, "# name <active_objs> <num_objs> <objsize> "
|
|
"<objperslab> <pagesperslab>");
|
|
seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
|
|
seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
|
|
#ifdef CONFIG_DEBUG_SLAB
|
|
seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
|
|
"<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
|
|
seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
|
|
#endif
|
|
seq_putc(m, '\n');
|
|
}
|
|
|
|
static void *s_start(struct seq_file *m, loff_t *pos)
|
|
{
|
|
loff_t n = *pos;
|
|
|
|
mutex_lock(&slab_mutex);
|
|
if (!n)
|
|
print_slabinfo_header(m);
|
|
|
|
return seq_list_start(&slab_caches, *pos);
|
|
}
|
|
|
|
void *slab_next(struct seq_file *m, void *p, loff_t *pos)
|
|
{
|
|
return seq_list_next(p, &slab_caches, pos);
|
|
}
|
|
|
|
void slab_stop(struct seq_file *m, void *p)
|
|
{
|
|
mutex_unlock(&slab_mutex);
|
|
}
|
|
|
|
static void
|
|
memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
|
|
{
|
|
struct kmem_cache *c;
|
|
struct slabinfo sinfo;
|
|
int i;
|
|
|
|
if (!is_root_cache(s))
|
|
return;
|
|
|
|
for_each_memcg_cache_index(i) {
|
|
c = cache_from_memcg_idx(s, i);
|
|
if (!c)
|
|
continue;
|
|
|
|
memset(&sinfo, 0, sizeof(sinfo));
|
|
get_slabinfo(c, &sinfo);
|
|
|
|
info->active_slabs += sinfo.active_slabs;
|
|
info->num_slabs += sinfo.num_slabs;
|
|
info->shared_avail += sinfo.shared_avail;
|
|
info->active_objs += sinfo.active_objs;
|
|
info->num_objs += sinfo.num_objs;
|
|
}
|
|
}
|
|
|
|
int cache_show(struct kmem_cache *s, struct seq_file *m)
|
|
{
|
|
struct slabinfo sinfo;
|
|
|
|
memset(&sinfo, 0, sizeof(sinfo));
|
|
get_slabinfo(s, &sinfo);
|
|
|
|
memcg_accumulate_slabinfo(s, &sinfo);
|
|
|
|
seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
|
|
cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
|
|
sinfo.objects_per_slab, (1 << sinfo.cache_order));
|
|
|
|
seq_printf(m, " : tunables %4u %4u %4u",
|
|
sinfo.limit, sinfo.batchcount, sinfo.shared);
|
|
seq_printf(m, " : slabdata %6lu %6lu %6lu",
|
|
sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
|
|
slabinfo_show_stats(m, s);
|
|
seq_putc(m, '\n');
|
|
return 0;
|
|
}
|
|
|
|
static int s_show(struct seq_file *m, void *p)
|
|
{
|
|
struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
|
|
|
|
if (!is_root_cache(s))
|
|
return 0;
|
|
return cache_show(s, m);
|
|
}
|
|
|
|
/*
|
|
* slabinfo_op - iterator that generates /proc/slabinfo
|
|
*
|
|
* Output layout:
|
|
* cache-name
|
|
* num-active-objs
|
|
* total-objs
|
|
* object size
|
|
* num-active-slabs
|
|
* total-slabs
|
|
* num-pages-per-slab
|
|
* + further values on SMP and with statistics enabled
|
|
*/
|
|
static const struct seq_operations slabinfo_op = {
|
|
.start = s_start,
|
|
.next = slab_next,
|
|
.stop = slab_stop,
|
|
.show = s_show,
|
|
};
|
|
|
|
static int slabinfo_open(struct inode *inode, struct file *file)
|
|
{
|
|
return seq_open(file, &slabinfo_op);
|
|
}
|
|
|
|
static const struct file_operations proc_slabinfo_operations = {
|
|
.open = slabinfo_open,
|
|
.read = seq_read,
|
|
.write = slabinfo_write,
|
|
.llseek = seq_lseek,
|
|
.release = seq_release,
|
|
};
|
|
|
|
static int __init slab_proc_init(void)
|
|
{
|
|
proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
|
|
&proc_slabinfo_operations);
|
|
return 0;
|
|
}
|
|
module_init(slab_proc_init);
|
|
#endif /* CONFIG_SLABINFO */
|
|
|
|
static __always_inline void *__do_krealloc(const void *p, size_t new_size,
|
|
gfp_t flags)
|
|
{
|
|
void *ret;
|
|
size_t ks = 0;
|
|
|
|
if (p)
|
|
ks = ksize(p);
|
|
|
|
if (ks >= new_size)
|
|
return (void *)p;
|
|
|
|
ret = kmalloc_track_caller(new_size, flags);
|
|
if (ret && p)
|
|
memcpy(ret, p, ks);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* __krealloc - like krealloc() but don't free @p.
|
|
* @p: object to reallocate memory for.
|
|
* @new_size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate.
|
|
*
|
|
* This function is like krealloc() except it never frees the originally
|
|
* allocated buffer. Use this if you don't want to free the buffer immediately
|
|
* like, for example, with RCU.
|
|
*/
|
|
void *__krealloc(const void *p, size_t new_size, gfp_t flags)
|
|
{
|
|
if (unlikely(!new_size))
|
|
return ZERO_SIZE_PTR;
|
|
|
|
return __do_krealloc(p, new_size, flags);
|
|
|
|
}
|
|
EXPORT_SYMBOL(__krealloc);
|
|
|
|
/**
|
|
* krealloc - reallocate memory. The contents will remain unchanged.
|
|
* @p: object to reallocate memory for.
|
|
* @new_size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate.
|
|
*
|
|
* The contents of the object pointed to are preserved up to the
|
|
* lesser of the new and old sizes. If @p is %NULL, krealloc()
|
|
* behaves exactly like kmalloc(). If @new_size is 0 and @p is not a
|
|
* %NULL pointer, the object pointed to is freed.
|
|
*/
|
|
void *krealloc(const void *p, size_t new_size, gfp_t flags)
|
|
{
|
|
void *ret;
|
|
|
|
if (unlikely(!new_size)) {
|
|
kfree(p);
|
|
return ZERO_SIZE_PTR;
|
|
}
|
|
|
|
ret = __do_krealloc(p, new_size, flags);
|
|
if (ret && p != ret)
|
|
kfree(p);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(krealloc);
|
|
|
|
/**
|
|
* kzfree - like kfree but zero memory
|
|
* @p: object to free memory of
|
|
*
|
|
* The memory of the object @p points to is zeroed before freed.
|
|
* If @p is %NULL, kzfree() does nothing.
|
|
*
|
|
* Note: this function zeroes the whole allocated buffer which can be a good
|
|
* deal bigger than the requested buffer size passed to kmalloc(). So be
|
|
* careful when using this function in performance sensitive code.
|
|
*/
|
|
void kzfree(const void *p)
|
|
{
|
|
size_t ks;
|
|
void *mem = (void *)p;
|
|
|
|
if (unlikely(ZERO_OR_NULL_PTR(mem)))
|
|
return;
|
|
ks = ksize(mem);
|
|
memset(mem, 0, ks);
|
|
kfree(mem);
|
|
}
|
|
EXPORT_SYMBOL(kzfree);
|
|
|
|
/* Tracepoints definitions. */
|
|
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
|
|
EXPORT_TRACEPOINT_SYMBOL(kfree);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
|