mm: memcg/slab: use a single set of kmem_caches for all accounted allocations

This is fairly big but mostly red patch, which makes all accounted slab
allocations use a single set of kmem_caches instead of creating a separate
set for each memory cgroup.

Because the number of non-root kmem_caches is now capped by the number of
root kmem_caches, there is no need to shrink or destroy them prematurely.
They can be perfectly destroyed together with their root counterparts.
This allows to dramatically simplify the management of non-root
kmem_caches and delete a ton of code.

This patch performs the following changes:
1) introduces memcg_params.memcg_cache pointer to represent the
   kmem_cache which will be used for all non-root allocations
2) reuses the existing memcg kmem_cache creation mechanism
   to create memcg kmem_cache on the first allocation attempt
3) memcg kmem_caches are named <kmemcache_name>-memcg,
   e.g. dentry-memcg
4) simplifies memcg_kmem_get_cache() to just return memcg kmem_cache
   or schedule it's creation and return the root cache
5) removes almost all non-root kmem_cache management code
   (separate refcounter, reparenting, shrinking, etc)
6) makes slab debugfs to display root_mem_cgroup css id and never
   show :dead and :deact flags in the memcg_slabinfo attribute.

Following patches in the series will simplify the kmem_cache creation.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-13-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Roman Gushchin 2020-08-06 23:21:10 -07:00 committed by Linus Torvalds
parent 0f876e4dc5
commit 9855609bde
7 changed files with 133 additions and 697 deletions

View File

@ -317,7 +317,6 @@ struct mem_cgroup {
/* Index in the kmem_cache->memcg_params.memcg_caches array */
int kmemcg_id;
enum memcg_kmem_state kmem_state;
struct list_head kmem_caches;
struct obj_cgroup __rcu *objcg;
struct list_head objcg_list; /* list of inherited objcgs */
#endif
@ -1404,9 +1403,7 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
}
#endif
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
struct obj_cgroup **objcgp);
void memcg_kmem_put_cache(struct kmem_cache *cachep);
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
#ifdef CONFIG_MEMCG_KMEM
int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp,

View File

@ -155,8 +155,7 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name,
void kmem_cache_destroy(struct kmem_cache *);
int kmem_cache_shrink(struct kmem_cache *);
void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *);
void memcg_create_kmem_cache(struct kmem_cache *cachep);
/*
* Please use this macro to create slab caches. Simply specify the
@ -580,8 +579,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
return __kmalloc_node(size, flags, node);
}
int memcg_update_all_caches(int num_memcgs);
/**
* kmalloc_array - allocate memory for an array.
* @n: number of elements.

View File

@ -350,7 +350,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
}
/*
* This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
* This will be used as a shrinker list's index.
* The main reason for not using cgroup id for this:
* this works better in sparse environments, where we have a lot of memcgs,
* but only a few kmem-limited. Or also, if we have, for instance, 200
@ -569,20 +569,16 @@ ino_t page_cgroup_ino(struct page *page)
unsigned long ino = 0;
rcu_read_lock();
if (PageSlab(page) && !PageTail(page)) {
memcg = memcg_from_slab_page(page);
} else {
memcg = page->mem_cgroup;
memcg = page->mem_cgroup;
/*
* The lowest bit set means that memcg isn't a valid
* memcg pointer, but a obj_cgroups pointer.
* In this case the page is shared and doesn't belong
* to any specific memory cgroup.
*/
if ((unsigned long) memcg & 0x1UL)
memcg = NULL;
}
/*
* The lowest bit set means that memcg isn't a valid
* memcg pointer, but a obj_cgroups pointer.
* In this case the page is shared and doesn't belong
* to any specific memory cgroup.
*/
if ((unsigned long) memcg & 0x1UL)
memcg = NULL;
while (memcg && !(memcg->css.flags & CSS_ONLINE))
memcg = parent_mem_cgroup(memcg);
@ -2822,12 +2818,18 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
page = virt_to_head_page(p);
/*
* Slab pages don't have page->mem_cgroup set because corresponding
* kmem caches can be reparented during the lifetime. That's why
* memcg_from_slab_page() should be used instead.
* Slab objects are accounted individually, not per-page.
* Memcg membership data for each individual object is saved in
* the page->obj_cgroups.
*/
if (PageSlab(page))
return memcg_from_slab_page(page);
if (page_has_obj_cgroups(page)) {
struct obj_cgroup *objcg;
unsigned int off;
off = obj_to_index(page->slab_cache, page, p);
objcg = page_obj_cgroups(page)[off];
return obj_cgroup_memcg(objcg);
}
/* All other pages use page->mem_cgroup */
return page->mem_cgroup;
@ -2882,9 +2884,7 @@ static int memcg_alloc_cache_id(void)
else if (size > MEMCG_CACHES_MAX_SIZE)
size = MEMCG_CACHES_MAX_SIZE;
err = memcg_update_all_caches(size);
if (!err)
err = memcg_update_all_list_lrus(size);
err = memcg_update_all_list_lrus(size);
if (!err)
memcg_nr_cache_ids = size;
@ -2903,7 +2903,6 @@ static void memcg_free_cache_id(int id)
}
struct memcg_kmem_cache_create_work {
struct mem_cgroup *memcg;
struct kmem_cache *cachep;
struct work_struct work;
};
@ -2912,33 +2911,24 @@ static void memcg_kmem_cache_create_func(struct work_struct *w)
{
struct memcg_kmem_cache_create_work *cw =
container_of(w, struct memcg_kmem_cache_create_work, work);
struct mem_cgroup *memcg = cw->memcg;
struct kmem_cache *cachep = cw->cachep;
memcg_create_kmem_cache(memcg, cachep);
memcg_create_kmem_cache(cachep);
css_put(&memcg->css);
kfree(cw);
}
/*
* Enqueue the creation of a per-memcg kmem_cache.
*/
static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
struct kmem_cache *cachep)
static void memcg_schedule_kmem_cache_create(struct kmem_cache *cachep)
{
struct memcg_kmem_cache_create_work *cw;
if (!css_tryget_online(&memcg->css))
return;
cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
if (!cw) {
css_put(&memcg->css);
if (!cw)
return;
}
cw->memcg = memcg;
cw->cachep = cachep;
INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
@ -2946,102 +2936,26 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
}
/**
* memcg_kmem_get_cache: select the correct per-memcg cache for allocation
* memcg_kmem_get_cache: select memcg or root cache for allocation
* @cachep: the original global kmem cache
*
* Return the kmem_cache we're supposed to use for a slab allocation.
* We try to use the current memcg's version of the cache.
*
* If the cache does not exist yet, if we are the first user of it, we
* create it asynchronously in a workqueue and let the current allocation
* go through with the original cache.
*
* This function takes a reference to the cache it returns to assure it
* won't get destroyed while we are working with it. Once the caller is
* done with it, memcg_kmem_put_cache() must be called to release the
* reference.
*/
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep,
struct obj_cgroup **objcgp)
struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
{
struct mem_cgroup *memcg;
struct kmem_cache *memcg_cachep;
struct memcg_cache_array *arr;
int kmemcg_id;
VM_BUG_ON(!is_root_cache(cachep));
if (memcg_kmem_bypass())
memcg_cachep = READ_ONCE(cachep->memcg_params.memcg_cache);
if (unlikely(!memcg_cachep)) {
memcg_schedule_kmem_cache_create(cachep);
return cachep;
rcu_read_lock();
if (unlikely(current->active_memcg))
memcg = current->active_memcg;
else
memcg = mem_cgroup_from_task(current);
if (!memcg || memcg == root_mem_cgroup)
goto out_unlock;
kmemcg_id = READ_ONCE(memcg->kmemcg_id);
if (kmemcg_id < 0)
goto out_unlock;
arr = rcu_dereference(cachep->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 the data dependency
* barrier inside READ_ONCE() (see memcg_create_kmem_cache()).
*/
memcg_cachep = READ_ONCE(arr->entries[kmemcg_id]);
/*
* If we are in a safe context (can wait, and not in interrupt
* context), we could be be predictable and return right away.
* This would guarantee that the allocation being performed
* already belongs in the new cache.
*
* However, there are some clashes that can arrive from locking.
* For instance, because we acquire the slab_mutex while doing
* memcg_create_kmem_cache, this means no further allocation
* could happen with the slab_mutex held. So it's better to
* defer everything.
*
* If the memcg is dying or memcg_cache is about to be released,
* don't bother creating new kmem_caches. Because memcg_cachep
* is ZEROed as the fist step of kmem offlining, we don't need
* percpu_ref_tryget_live() here. css_tryget_online() check in
* memcg_schedule_kmem_cache_create() will prevent us from
* creation of a new kmem_cache.
*/
if (unlikely(!memcg_cachep))
memcg_schedule_kmem_cache_create(memcg, cachep);
else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt)) {
struct obj_cgroup *objcg = rcu_dereference(memcg->objcg);
if (!objcg || !obj_cgroup_tryget(objcg)) {
percpu_ref_put(&memcg_cachep->memcg_params.refcnt);
goto out_unlock;
}
*objcgp = objcg;
cachep = memcg_cachep;
}
out_unlock:
rcu_read_unlock();
return cachep;
}
/**
* memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache
* @cachep: the cache returned by memcg_kmem_get_cache
*/
void memcg_kmem_put_cache(struct kmem_cache *cachep)
{
if (!is_root_cache(cachep))
percpu_ref_put(&cachep->memcg_params.refcnt);
return memcg_cachep;
}
/**
@ -3731,7 +3645,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
*/
memcg->kmemcg_id = memcg_id;
memcg->kmem_state = KMEM_ONLINE;
INIT_LIST_HEAD(&memcg->kmem_caches);
return 0;
}
@ -3744,22 +3657,13 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
if (memcg->kmem_state != KMEM_ONLINE)
return;
/*
* Clear the online state before clearing memcg_caches array
* entries. The slab_mutex in memcg_deactivate_kmem_caches()
* guarantees that no cache will be created for this cgroup
* after we are done (see memcg_create_kmem_cache()).
*/
memcg->kmem_state = KMEM_ALLOCATED;
parent = parent_mem_cgroup(memcg);
if (!parent)
parent = root_mem_cgroup;
/*
* Deactivate and reparent kmem_caches and objcgs.
*/
memcg_deactivate_kmem_caches(memcg, parent);
memcg_reparent_objcgs(memcg, parent);
kmemcg_id = memcg->kmemcg_id;
@ -5384,9 +5288,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
/* The following stuff does not apply to the root */
if (!parent) {
#ifdef CONFIG_MEMCG_KMEM
INIT_LIST_HEAD(&memcg->kmem_caches);
#endif
root_mem_cgroup = memcg;
return &memcg->css;
}

View File

@ -1249,7 +1249,7 @@ void __init kmem_cache_init(void)
nr_node_ids * sizeof(struct kmem_cache_node *),
SLAB_HWCACHE_ALIGN, 0, 0);
list_add(&kmem_cache->list, &slab_caches);
memcg_link_cache(kmem_cache, NULL);
memcg_link_cache(kmem_cache);
slab_state = PARTIAL;
/*
@ -2253,17 +2253,6 @@ int __kmem_cache_shrink(struct kmem_cache *cachep)
return (ret ? 1 : 0);
}
#ifdef CONFIG_MEMCG
void __kmemcg_cache_deactivate(struct kmem_cache *cachep)
{
__kmem_cache_shrink(cachep);
}
void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
{
}
#endif
int __kmem_cache_shutdown(struct kmem_cache *cachep)
{
return __kmem_cache_shrink(cachep);
@ -3872,7 +3861,8 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
return ret;
lockdep_assert_held(&slab_mutex);
for_each_memcg_cache(c, cachep) {
c = memcg_cache(cachep);
if (c) {
/* return value determined by the root cache only */
__do_tune_cpucache(c, limit, batchcount, shared, gfp);
}

144
mm/slab.h
View File

@ -32,66 +32,25 @@ struct kmem_cache {
#else /* !CONFIG_SLOB */
struct memcg_cache_array {
struct rcu_head rcu;
struct kmem_cache *entries[0];
};
/*
* This is the main placeholder for memcg-related information in kmem caches.
* Both the root cache and the child caches will have it. For the root cache,
* this will hold a dynamically allocated array large enough to hold
* information about the currently limited memcgs in the system. To allow the
* array to be accessed without taking any locks, on relocation we free the old
* version only after a grace period.
*
* Root and child caches hold different metadata.
* Both the root cache and the child cache will have it. Some fields are used
* in both cases, other are specific to root caches.
*
* @root_cache: Common to root and child caches. NULL for root, pointer to
* the root cache for children.
*
* The following fields are specific to root caches.
*
* @memcg_caches: kmemcg ID indexed table of child caches. This table is
* used to index child cachces during allocation and cleared
* early during shutdown.
*
* @root_caches_node: List node for slab_root_caches list.
*
* @children: List of all child caches. While the child caches are also
* reachable through @memcg_caches, a child cache remains on
* this list until it is actually destroyed.
*
* The following fields are specific to child caches.
*
* @memcg: Pointer to the memcg this cache belongs to.
*
* @children_node: List node for @root_cache->children list.
*
* @kmem_caches_node: List node for @memcg->kmem_caches list.
* @memcg_cache: pointer to memcg kmem cache, used by all non-root memory
* cgroups.
* @root_caches_node: list node for slab_root_caches list.
*/
struct memcg_cache_params {
struct kmem_cache *root_cache;
union {
struct {
struct memcg_cache_array __rcu *memcg_caches;
struct list_head __root_caches_node;
struct list_head children;
bool dying;
};
struct {
struct mem_cgroup *memcg;
struct list_head children_node;
struct list_head kmem_caches_node;
struct percpu_ref refcnt;
void (*work_fn)(struct kmem_cache *);
union {
struct rcu_head rcu_head;
struct work_struct work;
};
};
};
struct kmem_cache *memcg_cache;
struct list_head __root_caches_node;
};
#endif /* CONFIG_SLOB */
@ -236,8 +195,6 @@ 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 __kmemcg_cache_deactivate(struct kmem_cache *s);
void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s);
void slab_kmem_cache_release(struct kmem_cache *);
void kmem_cache_shrink_all(struct kmem_cache *s);
@ -311,14 +268,6 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
extern struct list_head slab_root_caches;
#define root_caches_node memcg_params.__root_caches_node
/*
* 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.children, \
memcg_params.children_node)
static inline bool is_root_cache(struct kmem_cache *s)
{
return !s->memcg_params.root_cache;
@ -349,6 +298,13 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
return s->memcg_params.root_cache;
}
static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
{
if (is_root_cache(s))
return s->memcg_params.memcg_cache;
return NULL;
}
static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
{
/*
@ -361,25 +317,9 @@ static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
((unsigned long)page->obj_cgroups & ~0x1UL);
}
/*
* Expects a pointer to a slab page. Please note, that PageSlab() check
* isn't sufficient, as it returns true also for tail compound slab pages,
* which do not have slab_cache pointer set.
* So this function assumes that the page can pass PageSlab() && !PageTail()
* check.
*
* The kmem_cache can be reparented asynchronously. The caller must ensure
* the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex.
*/
static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
static inline bool page_has_obj_cgroups(struct page *page)
{
struct kmem_cache *s;
s = READ_ONCE(page->slab_cache);
if (s && !is_root_cache(s))
return READ_ONCE(s->memcg_params.memcg);
return NULL;
return ((unsigned long)page->obj_cgroups & 0x1UL);
}
static inline int memcg_alloc_page_obj_cgroups(struct page *page,
@ -418,17 +358,25 @@ static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
size_t objects, gfp_t flags)
{
struct kmem_cache *cachep;
struct obj_cgroup *objcg;
cachep = memcg_kmem_get_cache(s, objcgp);
if (memcg_kmem_bypass())
return s;
cachep = memcg_kmem_get_cache(s);
if (is_root_cache(cachep))
return s;
if (obj_cgroup_charge(*objcgp, flags, objects * obj_full_size(s))) {
obj_cgroup_put(*objcgp);
memcg_kmem_put_cache(cachep);
objcg = get_obj_cgroup_from_current();
if (!objcg)
return s;
if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
obj_cgroup_put(objcg);
cachep = NULL;
}
*objcgp = objcg;
return cachep;
}
@ -467,7 +415,6 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
}
}
obj_cgroup_put(objcg);
memcg_kmem_put_cache(s);
}
static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
@ -491,7 +438,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
}
extern void slab_init_memcg_params(struct kmem_cache *);
extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
extern void memcg_link_cache(struct kmem_cache *s);
#else /* CONFIG_MEMCG_KMEM */
@ -499,9 +446,6 @@ extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
#define slab_root_caches slab_caches
#define root_caches_node list
#define for_each_memcg_cache(iter, root) \
for ((void)(iter), (void)(root); 0; )
static inline bool is_root_cache(struct kmem_cache *s)
{
return true;
@ -523,7 +467,17 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
return s;
}
static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
{
return NULL;
}
static inline bool page_has_obj_cgroups(struct page *page)
{
return false;
}
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
{
return NULL;
}
@ -560,8 +514,7 @@ static inline void slab_init_memcg_params(struct kmem_cache *s)
{
}
static inline void memcg_link_cache(struct kmem_cache *s,
struct mem_cgroup *memcg)
static inline void memcg_link_cache(struct kmem_cache *s)
{
}
@ -582,17 +535,14 @@ static __always_inline int charge_slab_page(struct page *page,
gfp_t gfp, int order,
struct kmem_cache *s)
{
#ifdef CONFIG_MEMCG_KMEM
if (memcg_kmem_enabled() && !is_root_cache(s)) {
int ret;
ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
if (ret)
return ret;
percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order);
}
#endif
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
PAGE_SIZE << order);
return 0;
@ -601,12 +551,9 @@ static __always_inline int charge_slab_page(struct page *page,
static __always_inline void uncharge_slab_page(struct page *page, int order,
struct kmem_cache *s)
{
#ifdef CONFIG_MEMCG_KMEM
if (memcg_kmem_enabled() && !is_root_cache(s)) {
if (memcg_kmem_enabled() && !is_root_cache(s))
memcg_free_page_obj_cgroups(page);
percpu_ref_put_many(&s->memcg_params.refcnt, 1 << order);
}
#endif
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-(PAGE_SIZE << order));
}
@ -749,9 +696,6 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
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);
void *memcg_slab_start(struct seq_file *m, loff_t *pos);
void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
void memcg_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)

View File

@ -133,141 +133,36 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
#ifdef CONFIG_MEMCG_KMEM
LIST_HEAD(slab_root_caches);
static DEFINE_SPINLOCK(memcg_kmem_wq_lock);
static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref);
void slab_init_memcg_params(struct kmem_cache *s)
{
s->memcg_params.root_cache = NULL;
RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
INIT_LIST_HEAD(&s->memcg_params.children);
s->memcg_params.dying = false;
s->memcg_params.memcg_cache = NULL;
}
static int init_memcg_params(struct kmem_cache *s,
struct kmem_cache *root_cache)
static void init_memcg_params(struct kmem_cache *s,
struct kmem_cache *root_cache)
{
struct memcg_cache_array *arr;
if (root_cache) {
int ret = percpu_ref_init(&s->memcg_params.refcnt,
kmemcg_cache_shutdown,
0, GFP_KERNEL);
if (ret)
return ret;
if (root_cache)
s->memcg_params.root_cache = root_cache;
INIT_LIST_HEAD(&s->memcg_params.children_node);
INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
return 0;
}
slab_init_memcg_params(s);
if (!memcg_nr_cache_ids)
return 0;
arr = kvzalloc(sizeof(struct memcg_cache_array) +
memcg_nr_cache_ids * sizeof(void *),
GFP_KERNEL);
if (!arr)
return -ENOMEM;
RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr);
return 0;
else
slab_init_memcg_params(s);
}
static void destroy_memcg_params(struct kmem_cache *s)
void memcg_link_cache(struct kmem_cache *s)
{
if (is_root_cache(s)) {
kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
} else {
mem_cgroup_put(s->memcg_params.memcg);
WRITE_ONCE(s->memcg_params.memcg, NULL);
percpu_ref_exit(&s->memcg_params.refcnt);
}
}
static void free_memcg_params(struct rcu_head *rcu)
{
struct memcg_cache_array *old;
old = container_of(rcu, struct memcg_cache_array, rcu);
kvfree(old);
}
static int update_memcg_params(struct kmem_cache *s, int new_array_size)
{
struct memcg_cache_array *old, *new;
new = kvzalloc(sizeof(struct memcg_cache_array) +
new_array_size * sizeof(void *), GFP_KERNEL);
if (!new)
return -ENOMEM;
old = rcu_dereference_protected(s->memcg_params.memcg_caches,
lockdep_is_held(&slab_mutex));
if (old)
memcpy(new->entries, old->entries,
memcg_nr_cache_ids * sizeof(void *));
rcu_assign_pointer(s->memcg_params.memcg_caches, new);
if (old)
call_rcu(&old->rcu, free_memcg_params);
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_root_caches, root_caches_node) {
ret = update_memcg_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)
break;
}
mutex_unlock(&slab_mutex);
return ret;
}
void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg)
{
if (is_root_cache(s)) {
if (is_root_cache(s))
list_add(&s->root_caches_node, &slab_root_caches);
} else {
css_get(&memcg->css);
s->memcg_params.memcg = memcg;
list_add(&s->memcg_params.children_node,
&s->memcg_params.root_cache->memcg_params.children);
list_add(&s->memcg_params.kmem_caches_node,
&s->memcg_params.memcg->kmem_caches);
}
}
static void memcg_unlink_cache(struct kmem_cache *s)
{
if (is_root_cache(s)) {
if (is_root_cache(s))
list_del(&s->root_caches_node);
} else {
list_del(&s->memcg_params.children_node);
list_del(&s->memcg_params.kmem_caches_node);
}
}
#else
static inline int init_memcg_params(struct kmem_cache *s,
struct kmem_cache *root_cache)
{
return 0;
}
static inline void destroy_memcg_params(struct kmem_cache *s)
static inline void init_memcg_params(struct kmem_cache *s,
struct kmem_cache *root_cache)
{
}
@ -328,14 +223,6 @@ int slab_unmergeable(struct kmem_cache *s)
if (s->refcount < 0)
return 1;
#ifdef CONFIG_MEMCG_KMEM
/*
* Skip the dying kmem_cache.
*/
if (s->memcg_params.dying)
return 1;
#endif
return 0;
}
@ -390,7 +277,7 @@ static struct kmem_cache *create_cache(const char *name,
unsigned int object_size, unsigned int align,
slab_flags_t flags, unsigned int useroffset,
unsigned int usersize, void (*ctor)(void *),
struct mem_cgroup *memcg, struct kmem_cache *root_cache)
struct kmem_cache *root_cache)
{
struct kmem_cache *s;
int err;
@ -410,24 +297,20 @@ static struct kmem_cache *create_cache(const char *name,
s->useroffset = useroffset;
s->usersize = usersize;
err = init_memcg_params(s, root_cache);
if (err)
goto out_free_cache;
init_memcg_params(s, root_cache);
err = __kmem_cache_create(s, flags);
if (err)
goto out_free_cache;
s->refcount = 1;
list_add(&s->list, &slab_caches);
memcg_link_cache(s, memcg);
memcg_link_cache(s);
out:
if (err)
return ERR_PTR(err);
return s;
out_free_cache:
destroy_memcg_params(s);
kmem_cache_free(kmem_cache, s);
goto out;
}
@ -514,7 +397,7 @@ kmem_cache_create_usercopy(const char *name,
s = create_cache(cache_name, size,
calculate_alignment(flags, align, size),
flags, useroffset, usersize, ctor, NULL, NULL);
flags, useroffset, usersize, ctor, NULL);
if (IS_ERR(s)) {
err = PTR_ERR(s);
kfree_const(cache_name);
@ -639,51 +522,27 @@ static int shutdown_cache(struct kmem_cache *s)
#ifdef CONFIG_MEMCG_KMEM
/*
* memcg_create_kmem_cache - Create a cache for a memory cgroup.
* @memcg: The memory cgroup the new cache is for.
* memcg_create_kmem_cache - Create a cache for non-root memory cgroups.
* @root_cache: The parent of 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.
* requests going all non-root memory cgroups to @root_cache. The new cache
* inherits properties from its parent.
*/
void memcg_create_kmem_cache(struct mem_cgroup *memcg,
struct kmem_cache *root_cache)
void memcg_create_kmem_cache(struct kmem_cache *root_cache)
{
static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
struct cgroup_subsys_state *css = &memcg->css;
struct memcg_cache_array *arr;
struct kmem_cache *s = NULL;
char *cache_name;
int idx;
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
/*
* The memory cgroup could have been offlined while the cache
* creation work was pending.
*/
if (memcg->kmem_state != KMEM_ONLINE)
if (root_cache->memcg_params.memcg_cache)
goto out_unlock;
idx = memcg_cache_id(memcg);
arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches,
lockdep_is_held(&slab_mutex));
/*
* Since per-memcg caches are created asynchronously on first
* allocation (see memcg_kmem_get_cache()), several threads can try to
* create the same cache, but only one of them may succeed.
*/
if (arr->entries[idx])
goto out_unlock;
cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name,
css->serial_nr, memcg_name_buf);
cache_name = kasprintf(GFP_KERNEL, "%s-memcg", root_cache->name);
if (!cache_name)
goto out_unlock;
@ -691,7 +550,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
root_cache->align,
root_cache->flags & CACHE_CREATE_MASK,
root_cache->useroffset, root_cache->usersize,
root_cache->ctor, memcg, root_cache);
root_cache->ctor, root_cache);
/*
* If we could not create a memcg cache, do not complain, because
* that's not critical at all as we can always proceed with the root
@ -708,7 +567,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
* initialized.
*/
smp_wmb();
arr->entries[idx] = s;
root_cache->memcg_params.memcg_cache = s;
out_unlock:
mutex_unlock(&slab_mutex);
@ -717,200 +576,18 @@ out_unlock:
put_online_cpus();
}
static void kmemcg_workfn(struct work_struct *work)
{
struct kmem_cache *s = container_of(work, struct kmem_cache,
memcg_params.work);
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
s->memcg_params.work_fn(s);
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
}
static void kmemcg_rcufn(struct rcu_head *head)
{
struct kmem_cache *s = container_of(head, struct kmem_cache,
memcg_params.rcu_head);
/*
* We need to grab blocking locks. Bounce to ->work. The
* work item shares the space with the RCU head and can't be
* initialized earlier.
*/
INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
}
static void kmemcg_cache_shutdown_fn(struct kmem_cache *s)
{
WARN_ON(shutdown_cache(s));
}
static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref)
{
struct kmem_cache *s = container_of(percpu_ref, struct kmem_cache,
memcg_params.refcnt);
unsigned long flags;
spin_lock_irqsave(&memcg_kmem_wq_lock, flags);
if (s->memcg_params.root_cache->memcg_params.dying)
goto unlock;
s->memcg_params.work_fn = kmemcg_cache_shutdown_fn;
INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
unlock:
spin_unlock_irqrestore(&memcg_kmem_wq_lock, flags);
}
static void kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
{
__kmemcg_cache_deactivate_after_rcu(s);
percpu_ref_kill(&s->memcg_params.refcnt);
}
static void kmemcg_cache_deactivate(struct kmem_cache *s)
{
if (WARN_ON_ONCE(is_root_cache(s)))
return;
__kmemcg_cache_deactivate(s);
s->flags |= SLAB_DEACTIVATED;
/*
* memcg_kmem_wq_lock is used to synchronize memcg_params.dying
* flag and make sure that no new kmem_cache deactivation tasks
* are queued (see flush_memcg_workqueue() ).
*/
spin_lock_irq(&memcg_kmem_wq_lock);
if (s->memcg_params.root_cache->memcg_params.dying)
goto unlock;
s->memcg_params.work_fn = kmemcg_cache_deactivate_after_rcu;
call_rcu(&s->memcg_params.rcu_head, kmemcg_rcufn);
unlock:
spin_unlock_irq(&memcg_kmem_wq_lock);
}
void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg,
struct mem_cgroup *parent)
{
int idx;
struct memcg_cache_array *arr;
struct kmem_cache *s, *c;
unsigned int nr_reparented;
idx = memcg_cache_id(memcg);
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
list_for_each_entry(s, &slab_root_caches, root_caches_node) {
arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
lockdep_is_held(&slab_mutex));
c = arr->entries[idx];
if (!c)
continue;
kmemcg_cache_deactivate(c);
arr->entries[idx] = NULL;
}
nr_reparented = 0;
list_for_each_entry(s, &memcg->kmem_caches,
memcg_params.kmem_caches_node) {
WRITE_ONCE(s->memcg_params.memcg, parent);
css_put(&memcg->css);
nr_reparented++;
}
if (nr_reparented) {
list_splice_init(&memcg->kmem_caches,
&parent->kmem_caches);
css_get_many(&parent->css, nr_reparented);
}
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
}
static int shutdown_memcg_caches(struct kmem_cache *s)
{
struct memcg_cache_array *arr;
struct kmem_cache *c, *c2;
LIST_HEAD(busy);
int i;
BUG_ON(!is_root_cache(s));
/*
* First, shutdown active caches, i.e. caches that belong to online
* memory cgroups.
*/
arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
lockdep_is_held(&slab_mutex));
for_each_memcg_cache_index(i) {
c = arr->entries[i];
if (!c)
continue;
if (shutdown_cache(c))
/*
* The cache still has objects. Move it to a temporary
* list so as not to try to destroy it for a second
* time while iterating over inactive caches below.
*/
list_move(&c->memcg_params.children_node, &busy);
else
/*
* The cache is empty and will be destroyed soon. Clear
* the pointer to it in the memcg_caches array so that
* it will never be accessed even if the root cache
* stays alive.
*/
arr->entries[i] = NULL;
}
if (s->memcg_params.memcg_cache)
WARN_ON(shutdown_cache(s->memcg_params.memcg_cache));
/*
* Second, shutdown all caches left from memory cgroups that are now
* offline.
*/
list_for_each_entry_safe(c, c2, &s->memcg_params.children,
memcg_params.children_node)
shutdown_cache(c);
list_splice(&busy, &s->memcg_params.children);
/*
* A cache being destroyed must be empty. In particular, this means
* that all per memcg caches attached to it must be empty too.
*/
if (!list_empty(&s->memcg_params.children))
return -EBUSY;
return 0;
}
static void memcg_set_kmem_cache_dying(struct kmem_cache *s)
{
spin_lock_irq(&memcg_kmem_wq_lock);
s->memcg_params.dying = true;
spin_unlock_irq(&memcg_kmem_wq_lock);
}
static void flush_memcg_workqueue(struct kmem_cache *s)
{
/*
* SLAB and SLUB deactivate the kmem_caches through call_rcu. Make
* sure all registered rcu callbacks have been invoked.
*/
rcu_barrier();
/*
* SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
* deactivates the memcg kmem_caches through workqueue. Make sure all
@ -918,30 +595,21 @@ static void flush_memcg_workqueue(struct kmem_cache *s)
*/
if (likely(memcg_kmem_cache_wq))
flush_workqueue(memcg_kmem_cache_wq);
/*
* If we're racing with children kmem_cache deactivation, it might
* take another rcu grace period to complete their destruction.
* At this moment the corresponding percpu_ref_kill() call should be
* done, but it might take another rcu grace period to complete
* switching to the atomic mode.
* Please, note that we check without grabbing the slab_mutex. It's safe
* because at this moment the children list can't grow.
*/
if (!list_empty(&s->memcg_params.children))
rcu_barrier();
}
#else
static inline int shutdown_memcg_caches(struct kmem_cache *s)
{
return 0;
}
static inline void flush_memcg_workqueue(struct kmem_cache *s)
{
}
#endif /* CONFIG_MEMCG_KMEM */
void slab_kmem_cache_release(struct kmem_cache *s)
{
__kmem_cache_release(s);
destroy_memcg_params(s);
kfree_const(s->name);
kmem_cache_free(kmem_cache, s);
}
@ -953,6 +621,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
if (unlikely(!s))
return;
flush_memcg_workqueue(s);
get_online_cpus();
get_online_mems();
@ -962,22 +632,6 @@ void kmem_cache_destroy(struct kmem_cache *s)
if (s->refcount)
goto out_unlock;
#ifdef CONFIG_MEMCG_KMEM
memcg_set_kmem_cache_dying(s);
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
flush_memcg_workqueue(s);
get_online_cpus();
get_online_mems();
mutex_lock(&slab_mutex);
#endif
err = shutdown_memcg_caches(s);
if (!err)
err = shutdown_cache(s);
@ -1019,7 +673,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
EXPORT_SYMBOL(kmem_cache_shrink);
/**
* kmem_cache_shrink_all - shrink a cache and all memcg caches for root cache
* kmem_cache_shrink_all - shrink root and memcg caches
* @s: The cache pointer
*/
void kmem_cache_shrink_all(struct kmem_cache *s)
@ -1036,21 +690,11 @@ void kmem_cache_shrink_all(struct kmem_cache *s)
kasan_cache_shrink(s);
__kmem_cache_shrink(s);
/*
* We have to take the slab_mutex to protect from the memcg list
* modification.
*/
mutex_lock(&slab_mutex);
for_each_memcg_cache(c, s) {
/*
* Don't need to shrink deactivated memcg caches.
*/
if (s->flags & SLAB_DEACTIVATED)
continue;
c = memcg_cache(s);
if (c) {
kasan_cache_shrink(c);
__kmem_cache_shrink(c);
}
mutex_unlock(&slab_mutex);
put_online_mems();
put_online_cpus();
}
@ -1105,7 +749,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name,
create_boot_cache(s, name, size, flags, useroffset, usersize);
list_add(&s->list, &slab_caches);
memcg_link_cache(s, NULL);
memcg_link_cache(s);
s->refcount = 1;
return s;
}
@ -1483,7 +1127,8 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
if (!is_root_cache(s))
return;
for_each_memcg_cache(c, s) {
c = memcg_cache(s);
if (c) {
memset(&sinfo, 0, sizeof(sinfo));
get_slabinfo(c, &sinfo);
@ -1614,7 +1259,7 @@ module_init(slab_proc_init);
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_MEMCG_KMEM)
/*
* Display information about kmem caches that have child memcg caches.
* Display information about kmem caches that have memcg cache.
*/
static int memcg_slabinfo_show(struct seq_file *m, void *unused)
{
@ -1626,9 +1271,9 @@ static int memcg_slabinfo_show(struct seq_file *m, void *unused)
seq_puts(m, " <active_slabs> <num_slabs>\n");
list_for_each_entry(s, &slab_root_caches, root_caches_node) {
/*
* Skip kmem caches that don't have any memcg children.
* Skip kmem caches that don't have the memcg cache.
*/
if (list_empty(&s->memcg_params.children))
if (!s->memcg_params.memcg_cache)
continue;
memset(&sinfo, 0, sizeof(sinfo));
@ -1637,23 +1282,13 @@ static int memcg_slabinfo_show(struct seq_file *m, void *unused)
cache_name(s), sinfo.active_objs, sinfo.num_objs,
sinfo.active_slabs, sinfo.num_slabs);
for_each_memcg_cache(c, s) {
struct cgroup_subsys_state *css;
char *status = "";
css = &c->memcg_params.memcg->css;
if (!(css->flags & CSS_ONLINE))
status = ":dead";
else if (c->flags & SLAB_DEACTIVATED)
status = ":deact";
memset(&sinfo, 0, sizeof(sinfo));
get_slabinfo(c, &sinfo);
seq_printf(m, "%-17s %4d%-6s %6lu %6lu %6lu %6lu\n",
cache_name(c), css->id, status,
sinfo.active_objs, sinfo.num_objs,
sinfo.active_slabs, sinfo.num_slabs);
}
c = s->memcg_params.memcg_cache;
memset(&sinfo, 0, sizeof(sinfo));
get_slabinfo(c, &sinfo);
seq_printf(m, "%-17s %4d %6lu %6lu %6lu %6lu\n",
cache_name(c), root_mem_cgroup->css.id,
sinfo.active_objs, sinfo.num_objs,
sinfo.active_slabs, sinfo.num_slabs);
}
mutex_unlock(&slab_mutex);
return 0;

View File

@ -4204,36 +4204,6 @@ int __kmem_cache_shrink(struct kmem_cache *s)
return ret;
}
#ifdef CONFIG_MEMCG
void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
{
/*
* Called with all the locks held after a sched RCU grace period.
* Even if @s becomes empty after shrinking, we can't know that @s
* doesn't have allocations already in-flight and thus can't
* destroy @s until the associated memcg is released.
*
* However, let's remove the sysfs files for empty caches here.
* Each cache has a lot of interface files which aren't
* particularly useful for empty draining caches; otherwise, we can
* easily end up with millions of unnecessary sysfs files on
* systems which have a lot of memory and transient cgroups.
*/
if (!__kmem_cache_shrink(s))
sysfs_slab_remove(s);
}
void __kmemcg_cache_deactivate(struct kmem_cache *s)
{
/*
* Disable empty slabs caching. Used to avoid pinning offline
* memory cgroups by kmem pages that can be freed.
*/
slub_set_cpu_partial(s, 0);
s->min_partial = 0;
}
#endif /* CONFIG_MEMCG */
static int slab_mem_going_offline_callback(void *arg)
{
struct kmem_cache *s;
@ -4390,7 +4360,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
}
slab_init_memcg_params(s);
list_add(&s->list, &slab_caches);
memcg_link_cache(s, NULL);
memcg_link_cache(s);
return s;
}
@ -4458,7 +4428,8 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
s->object_size = max(s->object_size, size);
s->inuse = max(s->inuse, ALIGN(size, sizeof(void *)));
for_each_memcg_cache(c, s) {
c = memcg_cache(s);
if (c) {
c->object_size = s->object_size;
c->inuse = max(c->inuse, ALIGN(size, sizeof(void *)));
}
@ -5591,7 +5562,8 @@ static ssize_t slab_attr_store(struct kobject *kobj,
* directly either failed or succeeded, in which case we loop
* through the descendants with best-effort propagation.
*/
for_each_memcg_cache(c, s)
c = memcg_cache(s);
if (c)
attribute->store(c, buf, len);
mutex_unlock(&slab_mutex);
}