mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-06 02:24:14 +08:00
41eb5df1cb
Patch series "mm: memcg/slab: Fix objcg pointer array handling problem", v4.
Since the merging of the new slab memory controller in v5.9, the page
structure stores a pointer to objcg pointer array for slab pages. When
the slab has no used objects, it can be freed in free_slab() which will
call kfree() to free the objcg pointer array in
memcg_alloc_page_obj_cgroups(). If it happens that the objcg pointer
array is the last used object in its slab, that slab may then be freed
which may caused kfree() to be called again.
With the right workload, the slab cache may be set up in a way that allows
the recursive kfree() calling loop to nest deep enough to cause a kernel
stack overflow and panic the system. In fact, we have a reproducer that
can cause kernel stack overflow on a s390 system involving kmalloc-rcl-256
and kmalloc-rcl-128 slabs with the following kfree() loop recursively
called 74 times:
[ 285.520739] [<000000000ec432fc>] kfree+0x4bc/0x560 [ 285.520740]
[<000000000ec43466>] __free_slab+0xc6/0x228 [ 285.520741]
[<000000000ec41fc2>] __slab_free+0x3c2/0x3e0 [ 285.520742]
[<000000000ec432fc>] kfree+0x4bc/0x560 : While investigating this issue, I
also found an issue on the allocation side. If the objcg pointer array
happen to come from the same slab or a circular dependency linkage is
formed with multiple slabs, those affected slabs can never be freed again.
This patch series addresses these two issues by introducing a new set of
kmalloc-cg-<n> caches split from kmalloc-<n> caches. The new set will
only contain non-reclaimable and non-dma objects that are accounted in
memory cgroups whereas the old set are now for unaccounted objects only.
By making this split, all the objcg pointer arrays will come from the
kmalloc-<n> caches, but those caches will never hold any objcg pointer
array. As a result, deeply nested kfree() call and the unfreeable slab
problems are now gone.
This patch (of 4):
Since the merging of the new slab memory controller in v5.9, the page
structure may store a pointer to obj_cgroup pointer array for slab pages.
Currently, only the __GFP_ACCOUNT bit is masked off. However, the array
is not readily reclaimable and doesn't need to come from the DMA buffer.
So those GFP bits should be masked off as well.
Do the flag bit clearing at memcg_alloc_page_obj_cgroups() to make sure
that it is consistently applied no matter where it is called.
Link: https://lkml.kernel.org/r/20210505200610.13943-1-longman@redhat.com
Link: https://lkml.kernel.org/r/20210505200610.13943-2-longman@redhat.com
Fixes: 286e04b8ed
("mm: memcg/slab: allocate obj_cgroups for non-root slab pages")
Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.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>
642 lines
17 KiB
C
642 lines
17 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#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 */
|
|
slab_flags_t flags; /* Active flags on the slab */
|
|
unsigned int useroffset;/* Usercopy region offset */
|
|
unsigned int usersize; /* Usercopy region size */
|
|
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>
|
|
#include <linux/fault-inject.h>
|
|
#include <linux/kasan.h>
|
|
#include <linux/kmemleak.h>
|
|
#include <linux/random.h>
|
|
#include <linux/sched/mm.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;
|
|
|
|
/* A table of kmalloc cache names and sizes */
|
|
extern const struct kmalloc_info_struct {
|
|
const char *name[NR_KMALLOC_TYPES];
|
|
unsigned int size;
|
|
} kmalloc_info[];
|
|
|
|
#ifndef CONFIG_SLOB
|
|
/* Kmalloc array related functions */
|
|
void setup_kmalloc_cache_index_table(void);
|
|
void create_kmalloc_caches(slab_flags_t);
|
|
|
|
/* Find the kmalloc slab corresponding for a certain size */
|
|
struct kmem_cache *kmalloc_slab(size_t, gfp_t);
|
|
#endif
|
|
|
|
gfp_t kmalloc_fix_flags(gfp_t flags);
|
|
|
|
/* Functions provided by the slab allocators */
|
|
int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
|
|
|
|
struct kmem_cache *create_kmalloc_cache(const char *name, unsigned int size,
|
|
slab_flags_t flags, unsigned int useroffset,
|
|
unsigned int usersize);
|
|
extern void create_boot_cache(struct kmem_cache *, const char *name,
|
|
unsigned int size, slab_flags_t flags,
|
|
unsigned int useroffset, unsigned int usersize);
|
|
|
|
int slab_unmergeable(struct kmem_cache *s);
|
|
struct kmem_cache *find_mergeable(unsigned size, unsigned align,
|
|
slab_flags_t flags, const char *name, void (*ctor)(void *));
|
|
#ifndef CONFIG_SLOB
|
|
struct kmem_cache *
|
|
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
|
|
slab_flags_t flags, void (*ctor)(void *));
|
|
|
|
slab_flags_t kmem_cache_flags(unsigned int object_size,
|
|
slab_flags_t flags, const char *name);
|
|
#else
|
|
static inline struct kmem_cache *
|
|
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
|
|
slab_flags_t flags, void (*ctor)(void *))
|
|
{ return NULL; }
|
|
|
|
static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
|
|
slab_flags_t flags, const char *name)
|
|
{
|
|
return flags;
|
|
}
|
|
#endif
|
|
|
|
|
|
/* Legal flag mask for kmem_cache_create(), for various configurations */
|
|
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
|
|
SLAB_CACHE_DMA32 | SLAB_PANIC | \
|
|
SLAB_TYPESAFE_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_CONSISTENCY_CHECKS)
|
|
#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_ACCOUNT)
|
|
#elif defined(CONFIG_SLUB)
|
|
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_TEMPORARY | SLAB_ACCOUNT)
|
|
#else
|
|
#define SLAB_CACHE_FLAGS (0)
|
|
#endif
|
|
|
|
/* Common flags available with current configuration */
|
|
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
|
|
|
|
/* Common flags permitted for kmem_cache_create */
|
|
#define SLAB_FLAGS_PERMITTED (SLAB_CORE_FLAGS | \
|
|
SLAB_RED_ZONE | \
|
|
SLAB_POISON | \
|
|
SLAB_STORE_USER | \
|
|
SLAB_TRACE | \
|
|
SLAB_CONSISTENCY_CHECKS | \
|
|
SLAB_MEM_SPREAD | \
|
|
SLAB_NOLEAKTRACE | \
|
|
SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_TEMPORARY | \
|
|
SLAB_ACCOUNT)
|
|
|
|
bool __kmem_cache_empty(struct kmem_cache *);
|
|
int __kmem_cache_shutdown(struct kmem_cache *);
|
|
void __kmem_cache_release(struct kmem_cache *);
|
|
int __kmem_cache_shrink(struct kmem_cache *);
|
|
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);
|
|
|
|
/*
|
|
* Generic implementation of bulk operations
|
|
* These are useful for situations in which the allocator cannot
|
|
* perform optimizations. In that case segments of the object listed
|
|
* may be allocated or freed using these operations.
|
|
*/
|
|
void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
|
|
int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
|
|
|
|
static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
|
|
{
|
|
return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
|
|
NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
|
|
}
|
|
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
#ifdef CONFIG_SLUB_DEBUG_ON
|
|
DECLARE_STATIC_KEY_TRUE(slub_debug_enabled);
|
|
#else
|
|
DECLARE_STATIC_KEY_FALSE(slub_debug_enabled);
|
|
#endif
|
|
extern void print_tracking(struct kmem_cache *s, void *object);
|
|
long validate_slab_cache(struct kmem_cache *s);
|
|
#else
|
|
static inline void print_tracking(struct kmem_cache *s, void *object)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Returns true if any of the specified slub_debug flags is enabled for the
|
|
* cache. Use only for flags parsed by setup_slub_debug() as it also enables
|
|
* the static key.
|
|
*/
|
|
static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
|
|
{
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
|
|
if (static_branch_unlikely(&slub_debug_enabled))
|
|
return s->flags & flags;
|
|
#endif
|
|
return false;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
|
|
gfp_t gfp, bool new_page);
|
|
void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
|
|
enum node_stat_item idx, int nr);
|
|
|
|
static inline void memcg_free_page_obj_cgroups(struct page *page)
|
|
{
|
|
kfree(page_objcgs(page));
|
|
page->memcg_data = 0;
|
|
}
|
|
|
|
static inline size_t obj_full_size(struct kmem_cache *s)
|
|
{
|
|
/*
|
|
* For each accounted object there is an extra space which is used
|
|
* to store obj_cgroup membership. Charge it too.
|
|
*/
|
|
return s->size + sizeof(struct obj_cgroup *);
|
|
}
|
|
|
|
/*
|
|
* Returns false if the allocation should fail.
|
|
*/
|
|
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup **objcgp,
|
|
size_t objects, gfp_t flags)
|
|
{
|
|
struct obj_cgroup *objcg;
|
|
|
|
if (!memcg_kmem_enabled())
|
|
return true;
|
|
|
|
if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))
|
|
return true;
|
|
|
|
objcg = get_obj_cgroup_from_current();
|
|
if (!objcg)
|
|
return true;
|
|
|
|
if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
|
|
obj_cgroup_put(objcg);
|
|
return false;
|
|
}
|
|
|
|
*objcgp = objcg;
|
|
return true;
|
|
}
|
|
|
|
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg,
|
|
gfp_t flags, size_t size,
|
|
void **p)
|
|
{
|
|
struct page *page;
|
|
unsigned long off;
|
|
size_t i;
|
|
|
|
if (!memcg_kmem_enabled() || !objcg)
|
|
return;
|
|
|
|
for (i = 0; i < size; i++) {
|
|
if (likely(p[i])) {
|
|
page = virt_to_head_page(p[i]);
|
|
|
|
if (!page_objcgs(page) &&
|
|
memcg_alloc_page_obj_cgroups(page, s, flags,
|
|
false)) {
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
continue;
|
|
}
|
|
|
|
off = obj_to_index(s, page, p[i]);
|
|
obj_cgroup_get(objcg);
|
|
page_objcgs(page)[off] = objcg;
|
|
mod_objcg_state(objcg, page_pgdat(page),
|
|
cache_vmstat_idx(s), obj_full_size(s));
|
|
} else {
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
}
|
|
}
|
|
obj_cgroup_put(objcg);
|
|
}
|
|
|
|
static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
|
|
void **p, int objects)
|
|
{
|
|
struct kmem_cache *s;
|
|
struct obj_cgroup **objcgs;
|
|
struct obj_cgroup *objcg;
|
|
struct page *page;
|
|
unsigned int off;
|
|
int i;
|
|
|
|
if (!memcg_kmem_enabled())
|
|
return;
|
|
|
|
for (i = 0; i < objects; i++) {
|
|
if (unlikely(!p[i]))
|
|
continue;
|
|
|
|
page = virt_to_head_page(p[i]);
|
|
objcgs = page_objcgs(page);
|
|
if (!objcgs)
|
|
continue;
|
|
|
|
if (!s_orig)
|
|
s = page->slab_cache;
|
|
else
|
|
s = s_orig;
|
|
|
|
off = obj_to_index(s, page, p[i]);
|
|
objcg = objcgs[off];
|
|
if (!objcg)
|
|
continue;
|
|
|
|
objcgs[off] = NULL;
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
|
|
-obj_full_size(s));
|
|
obj_cgroup_put(objcg);
|
|
}
|
|
}
|
|
|
|
#else /* CONFIG_MEMCG_KMEM */
|
|
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int memcg_alloc_page_obj_cgroups(struct page *page,
|
|
struct kmem_cache *s, gfp_t gfp,
|
|
bool new_page)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void memcg_free_page_obj_cgroups(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup **objcgp,
|
|
size_t objects, gfp_t flags)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg,
|
|
gfp_t flags, size_t size,
|
|
void **p)
|
|
{
|
|
}
|
|
|
|
static inline void memcg_slab_free_hook(struct kmem_cache *s,
|
|
void **p, int objects)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
static inline struct kmem_cache *virt_to_cache(const void *obj)
|
|
{
|
|
struct page *page;
|
|
|
|
page = virt_to_head_page(obj);
|
|
if (WARN_ONCE(!PageSlab(page), "%s: Object is not a Slab page!\n",
|
|
__func__))
|
|
return NULL;
|
|
return page->slab_cache;
|
|
}
|
|
|
|
static __always_inline void account_slab_page(struct page *page, int order,
|
|
struct kmem_cache *s,
|
|
gfp_t gfp)
|
|
{
|
|
if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
|
|
memcg_alloc_page_obj_cgroups(page, s, gfp, true);
|
|
|
|
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
|
|
PAGE_SIZE << order);
|
|
}
|
|
|
|
static __always_inline void unaccount_slab_page(struct page *page, int order,
|
|
struct kmem_cache *s)
|
|
{
|
|
if (memcg_kmem_enabled())
|
|
memcg_free_page_obj_cgroups(page);
|
|
|
|
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
|
|
-(PAGE_SIZE << order));
|
|
}
|
|
|
|
static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
|
|
{
|
|
struct kmem_cache *cachep;
|
|
|
|
if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
|
|
!kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
|
|
return s;
|
|
|
|
cachep = virt_to_cache(x);
|
|
if (WARN(cachep && cachep != s,
|
|
"%s: Wrong slab cache. %s but object is from %s\n",
|
|
__func__, s->name, cachep->name))
|
|
print_tracking(cachep, x);
|
|
return cachep;
|
|
}
|
|
|
|
static inline size_t slab_ksize(const struct kmem_cache *s)
|
|
{
|
|
#ifndef CONFIG_SLUB
|
|
return s->object_size;
|
|
|
|
#else /* CONFIG_SLUB */
|
|
# ifdef CONFIG_SLUB_DEBUG
|
|
/*
|
|
* Debugging requires use of the padding between object
|
|
* and whatever may come after it.
|
|
*/
|
|
if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
|
|
return s->object_size;
|
|
# endif
|
|
if (s->flags & SLAB_KASAN)
|
|
return s->object_size;
|
|
/*
|
|
* If we have the need to store the freelist pointer
|
|
* back there or track user information then we can
|
|
* only use the space before that information.
|
|
*/
|
|
if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER))
|
|
return s->inuse;
|
|
/*
|
|
* Else we can use all the padding etc for the allocation
|
|
*/
|
|
return s->size;
|
|
#endif
|
|
}
|
|
|
|
static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup **objcgp,
|
|
size_t size, gfp_t flags)
|
|
{
|
|
flags &= gfp_allowed_mask;
|
|
|
|
might_alloc(flags);
|
|
|
|
if (should_failslab(s, flags))
|
|
return NULL;
|
|
|
|
if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags))
|
|
return NULL;
|
|
|
|
return s;
|
|
}
|
|
|
|
static inline void slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg, gfp_t flags,
|
|
size_t size, void **p, bool init)
|
|
{
|
|
size_t i;
|
|
|
|
flags &= gfp_allowed_mask;
|
|
|
|
/*
|
|
* As memory initialization might be integrated into KASAN,
|
|
* kasan_slab_alloc and initialization memset must be
|
|
* kept together to avoid discrepancies in behavior.
|
|
*
|
|
* As p[i] might get tagged, memset and kmemleak hook come after KASAN.
|
|
*/
|
|
for (i = 0; i < size; i++) {
|
|
p[i] = kasan_slab_alloc(s, p[i], flags, init);
|
|
if (p[i] && init && !kasan_has_integrated_init())
|
|
memset(p[i], 0, s->object_size);
|
|
kmemleak_alloc_recursive(p[i], s->object_size, 1,
|
|
s->flags, flags);
|
|
}
|
|
|
|
memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
|
|
}
|
|
|
|
#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 total_slabs; /* length of all slab lists */
|
|
unsigned long free_slabs; /* length of free slab list only */
|
|
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);
|
|
|
|
#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
|
|
void dump_unreclaimable_slab(void);
|
|
#else
|
|
static inline void dump_unreclaimable_slab(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
|
|
|
|
#ifdef CONFIG_SLAB_FREELIST_RANDOM
|
|
int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count,
|
|
gfp_t gfp);
|
|
void cache_random_seq_destroy(struct kmem_cache *cachep);
|
|
#else
|
|
static inline int cache_random_seq_create(struct kmem_cache *cachep,
|
|
unsigned int count, gfp_t gfp)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { }
|
|
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
|
|
|
|
static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
|
|
{
|
|
if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
|
|
&init_on_alloc)) {
|
|
if (c->ctor)
|
|
return false;
|
|
if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))
|
|
return flags & __GFP_ZERO;
|
|
return true;
|
|
}
|
|
return flags & __GFP_ZERO;
|
|
}
|
|
|
|
static inline bool slab_want_init_on_free(struct kmem_cache *c)
|
|
{
|
|
if (static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
|
|
&init_on_free))
|
|
return !(c->ctor ||
|
|
(c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)));
|
|
return false;
|
|
}
|
|
|
|
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG)
|
|
void debugfs_slab_release(struct kmem_cache *);
|
|
#else
|
|
static inline void debugfs_slab_release(struct kmem_cache *s) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_PRINTK
|
|
#define KS_ADDRS_COUNT 16
|
|
struct kmem_obj_info {
|
|
void *kp_ptr;
|
|
struct page *kp_page;
|
|
void *kp_objp;
|
|
unsigned long kp_data_offset;
|
|
struct kmem_cache *kp_slab_cache;
|
|
void *kp_ret;
|
|
void *kp_stack[KS_ADDRS_COUNT];
|
|
};
|
|
void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page);
|
|
#endif
|
|
|
|
#endif /* MM_SLAB_H */
|