mirror of
https://github.com/FEX-Emu/linux.git
synced 2024-12-24 02:18:54 +00:00
d6e0b7fa11
To speed up further allocations SLUB may store empty slabs in per cpu/node partial lists instead of freeing them immediately. This prevents per memcg caches destruction, because kmem caches created for a memory cgroup are only destroyed after the last page charged to the cgroup is freed. To fix this issue, this patch resurrects approach first proposed in [1]. It forbids SLUB to cache empty slabs after the memory cgroup that the cache belongs to was destroyed. It is achieved by setting kmem_cache's cpu_partial and min_partial constants to 0 and tuning put_cpu_partial() so that it would drop frozen empty slabs immediately if cpu_partial = 0. The runtime overhead is minimal. From all the hot functions, we only touch relatively cold put_cpu_partial(): we make it call unfreeze_partials() after freezing a slab that belongs to an offline memory cgroup. Since slab freezing exists to avoid moving slabs from/to a partial list on free/alloc, and there can't be allocations from dead caches, it shouldn't cause any overhead. We do have to disable preemption for put_cpu_partial() to achieve that though. The original patch was accepted well and even merged to the mm tree. However, I decided to withdraw it due to changes happening to the memcg core at that time. I had an idea of introducing per-memcg shrinkers for kmem caches, but now, as memcg has finally settled down, I do not see it as an option, because SLUB shrinker would be too costly to call since SLUB does not keep free slabs on a separate list. Besides, we currently do not even call per-memcg shrinkers for offline memcgs. Overall, it would introduce much more complexity to both SLUB and memcg than this small patch. Regarding to SLAB, there's no problem with it, because it shrinks per-cpu/node caches periodically. Thanks to list_lru reparenting, we no longer keep entries for offline cgroups in per-memcg arrays (such as memcg_cache_params->memcg_caches), so we do not have to bother if a per-memcg cache will be shrunk a bit later than it could be. [1] http://thread.gmane.org/gmane.linux.kernel.mm/118649/focus=118650 Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
381 lines
10 KiB
C
381 lines
10 KiB
C
#ifndef MM_SLAB_H
|
|
#define MM_SLAB_H
|
|
/*
|
|
* Internal slab definitions
|
|
*/
|
|
|
|
#ifdef CONFIG_SLOB
|
|
/*
|
|
* Common fields provided in kmem_cache by all slab allocators
|
|
* This struct is either used directly by the allocator (SLOB)
|
|
* or the allocator must include definitions for all fields
|
|
* provided in kmem_cache_common in their definition of kmem_cache.
|
|
*
|
|
* Once we can do anonymous structs (C11 standard) we could put a
|
|
* anonymous struct definition in these allocators so that the
|
|
* separate allocations in the kmem_cache structure of SLAB and
|
|
* SLUB is no longer needed.
|
|
*/
|
|
struct kmem_cache {
|
|
unsigned int object_size;/* The original size of the object */
|
|
unsigned int size; /* The aligned/padded/added on size */
|
|
unsigned int align; /* Alignment as calculated */
|
|
unsigned long flags; /* Active flags on the slab */
|
|
const char *name; /* Slab name for sysfs */
|
|
int refcount; /* Use counter */
|
|
void (*ctor)(void *); /* Called on object slot creation */
|
|
struct list_head list; /* List of all slab caches on the system */
|
|
};
|
|
|
|
#endif /* CONFIG_SLOB */
|
|
|
|
#ifdef CONFIG_SLAB
|
|
#include <linux/slab_def.h>
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLUB
|
|
#include <linux/slub_def.h>
|
|
#endif
|
|
|
|
#include <linux/memcontrol.h>
|
|
|
|
/*
|
|
* State of the slab allocator.
|
|
*
|
|
* This is used to describe the states of the allocator during bootup.
|
|
* Allocators use this to gradually bootstrap themselves. Most allocators
|
|
* have the problem that the structures used for managing slab caches are
|
|
* allocated from slab caches themselves.
|
|
*/
|
|
enum slab_state {
|
|
DOWN, /* No slab functionality yet */
|
|
PARTIAL, /* SLUB: kmem_cache_node available */
|
|
PARTIAL_NODE, /* SLAB: kmalloc size for node struct available */
|
|
UP, /* Slab caches usable but not all extras yet */
|
|
FULL /* Everything is working */
|
|
};
|
|
|
|
extern enum slab_state slab_state;
|
|
|
|
/* The slab cache mutex protects the management structures during changes */
|
|
extern struct mutex slab_mutex;
|
|
|
|
/* The list of all slab caches on the system */
|
|
extern struct list_head slab_caches;
|
|
|
|
/* The slab cache that manages slab cache information */
|
|
extern struct kmem_cache *kmem_cache;
|
|
|
|
unsigned long calculate_alignment(unsigned long flags,
|
|
unsigned long align, unsigned long size);
|
|
|
|
#ifndef CONFIG_SLOB
|
|
/* Kmalloc array related functions */
|
|
void create_kmalloc_caches(unsigned long);
|
|
|
|
/* Find the kmalloc slab corresponding for a certain size */
|
|
struct kmem_cache *kmalloc_slab(size_t, gfp_t);
|
|
#endif
|
|
|
|
|
|
/* Functions provided by the slab allocators */
|
|
extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags);
|
|
|
|
extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
|
|
unsigned long flags);
|
|
extern void create_boot_cache(struct kmem_cache *, const char *name,
|
|
size_t size, unsigned long flags);
|
|
|
|
int slab_unmergeable(struct kmem_cache *s);
|
|
struct kmem_cache *find_mergeable(size_t size, size_t align,
|
|
unsigned long flags, const char *name, void (*ctor)(void *));
|
|
#ifndef CONFIG_SLOB
|
|
struct kmem_cache *
|
|
__kmem_cache_alias(const char *name, size_t size, size_t align,
|
|
unsigned long flags, void (*ctor)(void *));
|
|
|
|
unsigned long kmem_cache_flags(unsigned long object_size,
|
|
unsigned long flags, const char *name,
|
|
void (*ctor)(void *));
|
|
#else
|
|
static inline struct kmem_cache *
|
|
__kmem_cache_alias(const char *name, size_t size, size_t align,
|
|
unsigned long flags, void (*ctor)(void *))
|
|
{ return NULL; }
|
|
|
|
static inline unsigned long kmem_cache_flags(unsigned long object_size,
|
|
unsigned long flags, const char *name,
|
|
void (*ctor)(void *))
|
|
{
|
|
return flags;
|
|
}
|
|
#endif
|
|
|
|
|
|
/* Legal flag mask for kmem_cache_create(), for various configurations */
|
|
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
|
|
SLAB_DESTROY_BY_RCU | SLAB_DEBUG_OBJECTS )
|
|
|
|
#if defined(CONFIG_DEBUG_SLAB)
|
|
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
|
|
#elif defined(CONFIG_SLUB_DEBUG)
|
|
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
|
|
SLAB_TRACE | SLAB_DEBUG_FREE)
|
|
#else
|
|
#define SLAB_DEBUG_FLAGS (0)
|
|
#endif
|
|
|
|
#if defined(CONFIG_SLAB)
|
|
#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
|
|
SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | SLAB_NOTRACK)
|
|
#elif defined(CONFIG_SLUB)
|
|
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_TEMPORARY | SLAB_NOTRACK)
|
|
#else
|
|
#define SLAB_CACHE_FLAGS (0)
|
|
#endif
|
|
|
|
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
|
|
|
|
int __kmem_cache_shutdown(struct kmem_cache *);
|
|
int __kmem_cache_shrink(struct kmem_cache *, bool);
|
|
void slab_kmem_cache_release(struct kmem_cache *);
|
|
|
|
struct seq_file;
|
|
struct file;
|
|
|
|
struct slabinfo {
|
|
unsigned long active_objs;
|
|
unsigned long num_objs;
|
|
unsigned long active_slabs;
|
|
unsigned long num_slabs;
|
|
unsigned long shared_avail;
|
|
unsigned int limit;
|
|
unsigned int batchcount;
|
|
unsigned int shared;
|
|
unsigned int objects_per_slab;
|
|
unsigned int cache_order;
|
|
};
|
|
|
|
void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
|
|
void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
|
|
ssize_t slabinfo_write(struct file *file, const char __user *buffer,
|
|
size_t count, loff_t *ppos);
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
/*
|
|
* Iterate over all memcg caches of the given root cache. The caller must hold
|
|
* slab_mutex.
|
|
*/
|
|
#define for_each_memcg_cache(iter, root) \
|
|
list_for_each_entry(iter, &(root)->memcg_params.list, \
|
|
memcg_params.list)
|
|
|
|
#define for_each_memcg_cache_safe(iter, tmp, root) \
|
|
list_for_each_entry_safe(iter, tmp, &(root)->memcg_params.list, \
|
|
memcg_params.list)
|
|
|
|
static inline bool is_root_cache(struct kmem_cache *s)
|
|
{
|
|
return s->memcg_params.is_root_cache;
|
|
}
|
|
|
|
static inline bool slab_equal_or_root(struct kmem_cache *s,
|
|
struct kmem_cache *p)
|
|
{
|
|
return p == s || p == s->memcg_params.root_cache;
|
|
}
|
|
|
|
/*
|
|
* We use suffixes to the name in memcg because we can't have caches
|
|
* created in the system with the same name. But when we print them
|
|
* locally, better refer to them with the base name
|
|
*/
|
|
static inline const char *cache_name(struct kmem_cache *s)
|
|
{
|
|
if (!is_root_cache(s))
|
|
s = s->memcg_params.root_cache;
|
|
return s->name;
|
|
}
|
|
|
|
/*
|
|
* Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
|
|
* That said the caller must assure the memcg's cache won't go away by either
|
|
* taking a css reference to the owner cgroup, or holding the slab_mutex.
|
|
*/
|
|
static inline struct kmem_cache *
|
|
cache_from_memcg_idx(struct kmem_cache *s, int idx)
|
|
{
|
|
struct kmem_cache *cachep;
|
|
struct memcg_cache_array *arr;
|
|
|
|
rcu_read_lock();
|
|
arr = rcu_dereference(s->memcg_params.memcg_caches);
|
|
|
|
/*
|
|
* Make sure we will access the up-to-date value. The code updating
|
|
* memcg_caches issues a write barrier to match this (see
|
|
* memcg_create_kmem_cache()).
|
|
*/
|
|
cachep = lockless_dereference(arr->entries[idx]);
|
|
rcu_read_unlock();
|
|
|
|
return cachep;
|
|
}
|
|
|
|
static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
|
|
{
|
|
if (is_root_cache(s))
|
|
return s;
|
|
return s->memcg_params.root_cache;
|
|
}
|
|
|
|
static __always_inline int memcg_charge_slab(struct kmem_cache *s,
|
|
gfp_t gfp, int order)
|
|
{
|
|
if (!memcg_kmem_enabled())
|
|
return 0;
|
|
if (is_root_cache(s))
|
|
return 0;
|
|
return memcg_charge_kmem(s->memcg_params.memcg, gfp, 1 << order);
|
|
}
|
|
|
|
static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
|
|
{
|
|
if (!memcg_kmem_enabled())
|
|
return;
|
|
if (is_root_cache(s))
|
|
return;
|
|
memcg_uncharge_kmem(s->memcg_params.memcg, 1 << order);
|
|
}
|
|
|
|
extern void slab_init_memcg_params(struct kmem_cache *);
|
|
|
|
#else /* !CONFIG_MEMCG_KMEM */
|
|
|
|
#define for_each_memcg_cache(iter, root) \
|
|
for ((void)(iter), (void)(root); 0; )
|
|
#define for_each_memcg_cache_safe(iter, tmp, root) \
|
|
for ((void)(iter), (void)(tmp), (void)(root); 0; )
|
|
|
|
static inline bool is_root_cache(struct kmem_cache *s)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline bool slab_equal_or_root(struct kmem_cache *s,
|
|
struct kmem_cache *p)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline const char *cache_name(struct kmem_cache *s)
|
|
{
|
|
return s->name;
|
|
}
|
|
|
|
static inline struct kmem_cache *
|
|
cache_from_memcg_idx(struct kmem_cache *s, int idx)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
|
|
{
|
|
return s;
|
|
}
|
|
|
|
static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
|
|
{
|
|
}
|
|
|
|
static inline void slab_init_memcg_params(struct kmem_cache *s)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
|
|
{
|
|
struct kmem_cache *cachep;
|
|
struct page *page;
|
|
|
|
/*
|
|
* When kmemcg is not being used, both assignments should return the
|
|
* same value. but we don't want to pay the assignment price in that
|
|
* case. If it is not compiled in, the compiler should be smart enough
|
|
* to not do even the assignment. In that case, slab_equal_or_root
|
|
* will also be a constant.
|
|
*/
|
|
if (!memcg_kmem_enabled() && !unlikely(s->flags & SLAB_DEBUG_FREE))
|
|
return s;
|
|
|
|
page = virt_to_head_page(x);
|
|
cachep = page->slab_cache;
|
|
if (slab_equal_or_root(cachep, s))
|
|
return cachep;
|
|
|
|
pr_err("%s: Wrong slab cache. %s but object is from %s\n",
|
|
__func__, cachep->name, s->name);
|
|
WARN_ON_ONCE(1);
|
|
return s;
|
|
}
|
|
|
|
#ifndef CONFIG_SLOB
|
|
/*
|
|
* The slab lists for all objects.
|
|
*/
|
|
struct kmem_cache_node {
|
|
spinlock_t list_lock;
|
|
|
|
#ifdef CONFIG_SLAB
|
|
struct list_head slabs_partial; /* partial list first, better asm code */
|
|
struct list_head slabs_full;
|
|
struct list_head slabs_free;
|
|
unsigned long free_objects;
|
|
unsigned int free_limit;
|
|
unsigned int colour_next; /* Per-node cache coloring */
|
|
struct array_cache *shared; /* shared per node */
|
|
struct alien_cache **alien; /* on other nodes */
|
|
unsigned long next_reap; /* updated without locking */
|
|
int free_touched; /* updated without locking */
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLUB
|
|
unsigned long nr_partial;
|
|
struct list_head partial;
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
atomic_long_t nr_slabs;
|
|
atomic_long_t total_objects;
|
|
struct list_head full;
|
|
#endif
|
|
#endif
|
|
|
|
};
|
|
|
|
static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
|
|
{
|
|
return s->node[node];
|
|
}
|
|
|
|
/*
|
|
* Iterator over all nodes. The body will be executed for each node that has
|
|
* a kmem_cache_node structure allocated (which is true for all online nodes)
|
|
*/
|
|
#define for_each_kmem_cache_node(__s, __node, __n) \
|
|
for (__node = 0; __node < nr_node_ids; __node++) \
|
|
if ((__n = get_node(__s, __node)))
|
|
|
|
#endif
|
|
|
|
void *slab_start(struct seq_file *m, loff_t *pos);
|
|
void *slab_next(struct seq_file *m, void *p, loff_t *pos);
|
|
void slab_stop(struct seq_file *m, void *p);
|
|
int memcg_slab_show(struct seq_file *m, void *p);
|
|
|
|
#endif /* MM_SLAB_H */
|