linux/mm/slab.h
Andrey Vagin 6f6b895189 memcg: check that kmem_cache has memcg_params before accessing it
If the system had a few memory groups and all of them were destroyed,
memcg_limited_groups_array_size has non-zero value, but all new caches
are created without memcg_params, because memcg_kmem_enabled() returns
false.

We try to enumirate child caches in a few places and all of them are
potentially dangerous.

For example my kernel is compiled with CONFIG_SLAB and it crashed when I
tryed to mount a NFS share after a few experiments with kmemcg.

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
  IP: [<ffffffff8118166a>] do_tune_cpucache+0x8a/0xd0
  PGD b942a067 PUD b999f067 PMD 0
  Oops: 0000 [#1] SMP
  Modules linked in: fscache(+) ip6table_filter ip6_tables iptable_filter ip_tables i2c_piix4 pcspkr virtio_net virtio_balloon i2c_core floppy
  CPU: 0 PID: 357 Comm: modprobe Not tainted 3.11.0-rc7+ #59
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  task: ffff8800b9f98240 ti: ffff8800ba32e000 task.ti: ffff8800ba32e000
  RIP: 0010:[<ffffffff8118166a>]  [<ffffffff8118166a>] do_tune_cpucache+0x8a/0xd0
  RSP: 0018:ffff8800ba32fb70  EFLAGS: 00010246
  RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000006
  RDX: 0000000000000000 RSI: ffff8800b9f98910 RDI: 0000000000000246
  RBP: ffff8800ba32fba0 R08: 0000000000000002 R09: 0000000000000004
  R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000010
  R13: 0000000000000008 R14: 00000000000000d0 R15: ffff8800375d0200
  FS:  00007f55f1378740(0000) GS:ffff8800bfa00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
  CR2: 00007f24feba57a0 CR3: 0000000037b51000 CR4: 00000000000006f0
  Call Trace:
    enable_cpucache+0x49/0x100
    setup_cpu_cache+0x215/0x280
    __kmem_cache_create+0x2fa/0x450
    kmem_cache_create_memcg+0x214/0x350
    kmem_cache_create+0x2b/0x30
    fscache_init+0x19b/0x230 [fscache]
    do_one_initcall+0xfa/0x1b0
    load_module+0x1c41/0x26d0
    SyS_finit_module+0x86/0xb0
    system_call_fastpath+0x16/0x1b

Signed-off-by: Andrey Vagin <avagin@openvz.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Glauber Costa <glommer@openvz.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-08-28 19:26:38 -07:00

278 lines
7.4 KiB
C

#ifndef MM_SLAB_H
#define MM_SLAB_H
/*
* Internal slab definitions
*/
/*
* 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_ARRAYCACHE, /* SLAB: kmalloc size for arraycache 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);
struct mem_cgroup;
#ifdef CONFIG_SLUB
struct kmem_cache *
__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *));
#else
static inline struct kmem_cache *
__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *))
{ return NULL; }
#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 *);
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
static inline bool is_root_cache(struct kmem_cache *s)
{
return !s->memcg_params || s->memcg_params->is_root_cache;
}
static inline bool cache_match_memcg(struct kmem_cache *cachep,
struct mem_cgroup *memcg)
{
return (is_root_cache(cachep) && !memcg) ||
(cachep->memcg_params->memcg == memcg);
}
static inline void memcg_bind_pages(struct kmem_cache *s, int order)
{
if (!is_root_cache(s))
atomic_add(1 << order, &s->memcg_params->nr_pages);
}
static inline void memcg_release_pages(struct kmem_cache *s, int order)
{
if (is_root_cache(s))
return;
if (atomic_sub_and_test((1 << order), &s->memcg_params->nr_pages))
mem_cgroup_destroy_cache(s);
}
static inline bool slab_equal_or_root(struct kmem_cache *s,
struct kmem_cache *p)
{
return (p == s) ||
(s->memcg_params && (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))
return s->memcg_params->root_cache->name;
return s->name;
}
static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
{
if (!s->memcg_params)
return NULL;
return s->memcg_params->memcg_caches[idx];
}
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;
}
#else
static inline bool is_root_cache(struct kmem_cache *s)
{
return true;
}
static inline bool cache_match_memcg(struct kmem_cache *cachep,
struct mem_cgroup *memcg)
{
return true;
}
static inline void memcg_bind_pages(struct kmem_cache *s, int order)
{
}
static inline void memcg_release_pages(struct kmem_cache *s, int order)
{
}
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(struct kmem_cache *s, int idx)
{
return NULL;
}
static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
{
return s;
}
#endif
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",
__FUNCTION__, cachep->name, s->name);
WARN_ON_ONCE(1);
return s;
}
#endif
/*
* 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 array_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
};
void *slab_next(struct seq_file *m, void *p, loff_t *pos);
void slab_stop(struct seq_file *m, void *p);