linux/mm/slab.h

293 lines
7.9 KiB
C
Raw Normal View History

#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 *
memcg, slab: never try to merge memcg caches When a kmem cache is created (kmem_cache_create_memcg()), we first try to find a compatible cache that already exists and can handle requests from the new cache, i.e. has the same object size, alignment, ctor, etc. If there is such a cache, we do not create any new caches, instead we simply increment the refcount of the cache found and return it. Currently we do this procedure not only when creating root caches, but also for memcg caches. However, there is no point in that, because, as every memcg cache has exactly the same parameters as its parent and cache merging cannot be turned off in runtime (only on boot by passing "slub_nomerge"), the root caches of any two potentially mergeable memcg caches should be merged already, i.e. it must be the same root cache, and therefore we couldn't even get to the memcg cache creation, because it already exists. The only exception is boot caches - they are explicitly forbidden to be merged by setting their refcount to -1. There are currently only two of them - kmem_cache and kmem_cache_node, which are used in slab internals (I do not count kmalloc caches as their refcount is set to 1 immediately after creation). Since they are prevented from merging preliminary I guess we should avoid to merge their children too. So let's remove the useless code responsible for merging memcg caches. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Glauber Costa <glommer@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-07 22:39:23 +00:00
__kmem_cache_alias(const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *));
#else
static inline struct kmem_cache *
memcg, slab: never try to merge memcg caches When a kmem cache is created (kmem_cache_create_memcg()), we first try to find a compatible cache that already exists and can handle requests from the new cache, i.e. has the same object size, alignment, ctor, etc. If there is such a cache, we do not create any new caches, instead we simply increment the refcount of the cache found and return it. Currently we do this procedure not only when creating root caches, but also for memcg caches. However, there is no point in that, because, as every memcg cache has exactly the same parameters as its parent and cache merging cannot be turned off in runtime (only on boot by passing "slub_nomerge"), the root caches of any two potentially mergeable memcg caches should be merged already, i.e. it must be the same root cache, and therefore we couldn't even get to the memcg cache creation, because it already exists. The only exception is boot caches - they are explicitly forbidden to be merged by setting their refcount to -1. There are currently only two of them - kmem_cache and kmem_cache_node, which are used in slab internals (I do not count kmalloc caches as their refcount is set to 1 immediately after creation). Since they are prevented from merging preliminary I guess we should avoid to merge their children too. So let's remove the useless code responsible for merging memcg caches. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Glauber Costa <glommer@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-07 22:39:23 +00:00
__kmem_cache_alias(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 *);
slub: use sysfs'es release mechanism for kmem_cache debugobjects warning during netfilter exit: ------------[ cut here ]------------ WARNING: CPU: 6 PID: 4178 at lib/debugobjects.c:260 debug_print_object+0x8d/0xb0() ODEBUG: free active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x20 Modules linked in: CPU: 6 PID: 4178 Comm: kworker/u16:2 Tainted: G W 3.11.0-next-20130906-sasha #3984 Workqueue: netns cleanup_net Call Trace: dump_stack+0x52/0x87 warn_slowpath_common+0x8c/0xc0 warn_slowpath_fmt+0x46/0x50 debug_print_object+0x8d/0xb0 __debug_check_no_obj_freed+0xa5/0x220 debug_check_no_obj_freed+0x15/0x20 kmem_cache_free+0x197/0x340 kmem_cache_destroy+0x86/0xe0 nf_conntrack_cleanup_net_list+0x131/0x170 nf_conntrack_pernet_exit+0x5d/0x70 ops_exit_list+0x5e/0x70 cleanup_net+0xfb/0x1c0 process_one_work+0x338/0x550 worker_thread+0x215/0x350 kthread+0xe7/0xf0 ret_from_fork+0x7c/0xb0 Also during dcookie cleanup: WARNING: CPU: 12 PID: 9725 at lib/debugobjects.c:260 debug_print_object+0x8c/0xb0() ODEBUG: free active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x20 Modules linked in: CPU: 12 PID: 9725 Comm: trinity-c141 Not tainted 3.15.0-rc2-next-20140423-sasha-00018-gc4ff6c4 #408 Call Trace: dump_stack (lib/dump_stack.c:52) warn_slowpath_common (kernel/panic.c:430) warn_slowpath_fmt (kernel/panic.c:445) debug_print_object (lib/debugobjects.c:262) __debug_check_no_obj_freed (lib/debugobjects.c:697) debug_check_no_obj_freed (lib/debugobjects.c:726) kmem_cache_free (mm/slub.c:2689 mm/slub.c:2717) kmem_cache_destroy (mm/slab_common.c:363) dcookie_unregister (fs/dcookies.c:302 fs/dcookies.c:343) event_buffer_release (arch/x86/oprofile/../../../drivers/oprofile/event_buffer.c:153) __fput (fs/file_table.c:217) ____fput (fs/file_table.c:253) task_work_run (kernel/task_work.c:125 (discriminator 1)) do_notify_resume (include/linux/tracehook.h:196 arch/x86/kernel/signal.c:751) int_signal (arch/x86/kernel/entry_64.S:807) Sysfs has a release mechanism. Use that to release the kmem_cache structure if CONFIG_SYSFS is enabled. Only slub is changed - slab currently only supports /proc/slabinfo and not /sys/kernel/slab/*. We talked about adding that and someone was working on it. [akpm@linux-foundation.org: fix CONFIG_SYSFS=n build] [akpm@linux-foundation.org: fix CONFIG_SYSFS=n build even more] Signed-off-by: Christoph Lameter <cl@linux.com> Reported-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Acked-by: Greg KH <greg@kroah.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Pekka Enberg <penberg@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Bart Van Assche <bvanassche@acm.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-05-06 19:50:08 +00:00
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
static inline bool is_root_cache(struct kmem_cache *s)
{
return !s->memcg_params || s->memcg_params->is_root_cache;
}
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;
}
/*
* 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. Since once
* created a memcg's cache is destroyed only along with the root cache, it is
* true if we are going to allocate from the cache or hold a reference to the
* root cache by other means. Otherwise, we should hold either the slab_mutex
* or the memcg's slab_caches_mutex while calling this function and accessing
* the returned value.
*/
static inline struct kmem_cache *
cache_from_memcg_idx(struct kmem_cache *s, int idx)
{
struct kmem_cache *cachep;
struct memcg_cache_params *params;
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 23:35:20 +00:00
if (!s->memcg_params)
return NULL;
rcu_read_lock();
params = rcu_dereference(s->memcg_params);
cachep = params->memcg_caches[idx];
rcu_read_unlock();
/*
* Make sure we will access the up-to-date value. The code updating
* memcg_caches issues a write barrier to match this (see
* memcg_register_cache()).
*/
smp_read_barrier_depends();
return cachep;
}
slab: propagate tunable values SLAB allows us to tune a particular cache behavior with tunables. When creating a new memcg cache copy, we'd like to preserve any tunables the parent cache already had. This could be done by an explicit call to do_tune_cpucache() after the cache is created. But this is not very convenient now that the caches are created from common code, since this function is SLAB-specific. Another method of doing that is taking advantage of the fact that do_tune_cpucache() is always called from enable_cpucache(), which is called at cache initialization. We can just preset the values, and then things work as expected. It can also happen that a root cache has its tunables updated during normal system operation. In this case, we will propagate the change to all caches that are already active. This change will require us to move the assignment of root_cache in memcg_params a bit earlier. We need this to be already set - which memcg_kmem_register_cache will do - when we reach __kmem_cache_create() Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <fweisbec@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: JoonSoo Kim <js1304@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Rik van Riel <riel@redhat.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 22:23:03 +00:00
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 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_idx(struct kmem_cache *s, int idx)
{
return NULL;
}
slab: propagate tunable values SLAB allows us to tune a particular cache behavior with tunables. When creating a new memcg cache copy, we'd like to preserve any tunables the parent cache already had. This could be done by an explicit call to do_tune_cpucache() after the cache is created. But this is not very convenient now that the caches are created from common code, since this function is SLAB-specific. Another method of doing that is taking advantage of the fact that do_tune_cpucache() is always called from enable_cpucache(), which is called at cache initialization. We can just preset the values, and then things work as expected. It can also happen that a root cache has its tunables updated during normal system operation. In this case, we will propagate the change to all caches that are already active. This change will require us to move the assignment of root_cache in memcg_params a bit earlier. We need this to be already set - which memcg_kmem_register_cache will do - when we reach __kmem_cache_create() Signed-off-by: Glauber Costa <glommer@parallels.com> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <fweisbec@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: JoonSoo Kim <js1304@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Hocko <mhocko@suse.cz> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Rik van Riel <riel@redhat.com> Cc: Suleiman Souhlal <suleiman@google.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 22:23:03 +00:00
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);