memcg: export struct mem_cgroup
mem_cgroup structure is defined in mm/memcontrol.c currently which means that the code outside of this file has to use external API even for trivial access stuff. This patch exports mm_struct with its dependencies and makes some of the exported functions inlines. This even helps to reduce the code size a bit (make defconfig + CONFIG_MEMCG=y) text data bss dec hex filename 12355346 1823792 1089536 15268674 e8fb42 vmlinux.before 12354970 1823792 1089536 15268298 e8f9ca vmlinux.after This is not much (370B) but better than nothing. We also save a function call in some hot paths like callers of mem_cgroup_count_vm_event which is used for accounting. The patch doesn't introduce any functional changes. [vdavykov@parallels.com: inline memcg_kmem_is_active] [vdavykov@parallels.com: do not expose type outside of CONFIG_MEMCG] [akpm@linux-foundation.org: memcontrol.h needs eventfd.h for eventfd_ctx] [akpm@linux-foundation.org: export mem_cgroup_from_task() to modules] Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: Vladimir Davydov <vdavydov@parallels.com> Suggested-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Michal Hocko
committed by
Linus Torvalds
Linus Torvalds
parent
b3d9ed3fd8
commit
33398cf2f3
315
mm/memcontrol.c
315
mm/memcontrol.c
@@ -111,56 +111,10 @@ static const char * const mem_cgroup_lru_names[] = {
|
||||
"unevictable",
|
||||
};
|
||||
|
||||
/*
|
||||
* Per memcg event counter is incremented at every pagein/pageout. With THP,
|
||||
* it will be incremated by the number of pages. This counter is used for
|
||||
* for trigger some periodic events. This is straightforward and better
|
||||
* than using jiffies etc. to handle periodic memcg event.
|
||||
*/
|
||||
enum mem_cgroup_events_target {
|
||||
MEM_CGROUP_TARGET_THRESH,
|
||||
MEM_CGROUP_TARGET_SOFTLIMIT,
|
||||
MEM_CGROUP_TARGET_NUMAINFO,
|
||||
MEM_CGROUP_NTARGETS,
|
||||
};
|
||||
#define THRESHOLDS_EVENTS_TARGET 128
|
||||
#define SOFTLIMIT_EVENTS_TARGET 1024
|
||||
#define NUMAINFO_EVENTS_TARGET 1024
|
||||
|
||||
struct mem_cgroup_stat_cpu {
|
||||
long count[MEM_CGROUP_STAT_NSTATS];
|
||||
unsigned long events[MEMCG_NR_EVENTS];
|
||||
unsigned long nr_page_events;
|
||||
unsigned long targets[MEM_CGROUP_NTARGETS];
|
||||
};
|
||||
|
||||
struct reclaim_iter {
|
||||
struct mem_cgroup *position;
|
||||
/* scan generation, increased every round-trip */
|
||||
unsigned int generation;
|
||||
};
|
||||
|
||||
/*
|
||||
* per-zone information in memory controller.
|
||||
*/
|
||||
struct mem_cgroup_per_zone {
|
||||
struct lruvec lruvec;
|
||||
unsigned long lru_size[NR_LRU_LISTS];
|
||||
|
||||
struct reclaim_iter iter[DEF_PRIORITY + 1];
|
||||
|
||||
struct rb_node tree_node; /* RB tree node */
|
||||
unsigned long usage_in_excess;/* Set to the value by which */
|
||||
/* the soft limit is exceeded*/
|
||||
bool on_tree;
|
||||
struct mem_cgroup *memcg; /* Back pointer, we cannot */
|
||||
/* use container_of */
|
||||
};
|
||||
|
||||
struct mem_cgroup_per_node {
|
||||
struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
|
||||
};
|
||||
|
||||
/*
|
||||
* Cgroups above their limits are maintained in a RB-Tree, independent of
|
||||
* their hierarchy representation
|
||||
@@ -181,32 +135,6 @@ struct mem_cgroup_tree {
|
||||
|
||||
static struct mem_cgroup_tree soft_limit_tree __read_mostly;
|
||||
|
||||
struct mem_cgroup_threshold {
|
||||
struct eventfd_ctx *eventfd;
|
||||
unsigned long threshold;
|
||||
};
|
||||
|
||||
/* For threshold */
|
||||
struct mem_cgroup_threshold_ary {
|
||||
/* An array index points to threshold just below or equal to usage. */
|
||||
int current_threshold;
|
||||
/* Size of entries[] */
|
||||
unsigned int size;
|
||||
/* Array of thresholds */
|
||||
struct mem_cgroup_threshold entries[0];
|
||||
};
|
||||
|
||||
struct mem_cgroup_thresholds {
|
||||
/* Primary thresholds array */
|
||||
struct mem_cgroup_threshold_ary *primary;
|
||||
/*
|
||||
* Spare threshold array.
|
||||
* This is needed to make mem_cgroup_unregister_event() "never fail".
|
||||
* It must be able to store at least primary->size - 1 entries.
|
||||
*/
|
||||
struct mem_cgroup_threshold_ary *spare;
|
||||
};
|
||||
|
||||
/* for OOM */
|
||||
struct mem_cgroup_eventfd_list {
|
||||
struct list_head list;
|
||||
@@ -256,113 +184,6 @@ struct mem_cgroup_event {
|
||||
static void mem_cgroup_threshold(struct mem_cgroup *memcg);
|
||||
static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
|
||||
|
||||
/*
|
||||
* The memory controller data structure. The memory controller controls both
|
||||
* page cache and RSS per cgroup. We would eventually like to provide
|
||||
* statistics based on the statistics developed by Rik Van Riel for clock-pro,
|
||||
* to help the administrator determine what knobs to tune.
|
||||
*/
|
||||
struct mem_cgroup {
|
||||
struct cgroup_subsys_state css;
|
||||
|
||||
/* Accounted resources */
|
||||
struct page_counter memory;
|
||||
struct page_counter memsw;
|
||||
struct page_counter kmem;
|
||||
|
||||
/* Normal memory consumption range */
|
||||
unsigned long low;
|
||||
unsigned long high;
|
||||
|
||||
unsigned long soft_limit;
|
||||
|
||||
/* vmpressure notifications */
|
||||
struct vmpressure vmpressure;
|
||||
|
||||
/* css_online() has been completed */
|
||||
int initialized;
|
||||
|
||||
/*
|
||||
* Should the accounting and control be hierarchical, per subtree?
|
||||
*/
|
||||
bool use_hierarchy;
|
||||
|
||||
/* protected by memcg_oom_lock */
|
||||
bool oom_lock;
|
||||
int under_oom;
|
||||
|
||||
int swappiness;
|
||||
/* OOM-Killer disable */
|
||||
int oom_kill_disable;
|
||||
|
||||
/* protect arrays of thresholds */
|
||||
struct mutex thresholds_lock;
|
||||
|
||||
/* thresholds for memory usage. RCU-protected */
|
||||
struct mem_cgroup_thresholds thresholds;
|
||||
|
||||
/* thresholds for mem+swap usage. RCU-protected */
|
||||
struct mem_cgroup_thresholds memsw_thresholds;
|
||||
|
||||
/* For oom notifier event fd */
|
||||
struct list_head oom_notify;
|
||||
|
||||
/*
|
||||
* Should we move charges of a task when a task is moved into this
|
||||
* mem_cgroup ? And what type of charges should we move ?
|
||||
*/
|
||||
unsigned long move_charge_at_immigrate;
|
||||
/*
|
||||
* set > 0 if pages under this cgroup are moving to other cgroup.
|
||||
*/
|
||||
atomic_t moving_account;
|
||||
/* taken only while moving_account > 0 */
|
||||
spinlock_t move_lock;
|
||||
struct task_struct *move_lock_task;
|
||||
unsigned long move_lock_flags;
|
||||
/*
|
||||
* percpu counter.
|
||||
*/
|
||||
struct mem_cgroup_stat_cpu __percpu *stat;
|
||||
spinlock_t pcp_counter_lock;
|
||||
|
||||
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
|
||||
struct cg_proto tcp_mem;
|
||||
#endif
|
||||
#if defined(CONFIG_MEMCG_KMEM)
|
||||
/* Index in the kmem_cache->memcg_params.memcg_caches array */
|
||||
int kmemcg_id;
|
||||
bool kmem_acct_activated;
|
||||
bool kmem_acct_active;
|
||||
#endif
|
||||
|
||||
int last_scanned_node;
|
||||
#if MAX_NUMNODES > 1
|
||||
nodemask_t scan_nodes;
|
||||
atomic_t numainfo_events;
|
||||
atomic_t numainfo_updating;
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_CGROUP_WRITEBACK
|
||||
struct list_head cgwb_list;
|
||||
struct wb_domain cgwb_domain;
|
||||
#endif
|
||||
|
||||
/* List of events which userspace want to receive */
|
||||
struct list_head event_list;
|
||||
spinlock_t event_list_lock;
|
||||
|
||||
struct mem_cgroup_per_node *nodeinfo[0];
|
||||
/* WARNING: nodeinfo must be the last member here */
|
||||
};
|
||||
|
||||
#ifdef CONFIG_MEMCG_KMEM
|
||||
bool memcg_kmem_is_active(struct mem_cgroup *memcg)
|
||||
{
|
||||
return memcg->kmem_acct_active;
|
||||
}
|
||||
#endif
|
||||
|
||||
/* Stuffs for move charges at task migration. */
|
||||
/*
|
||||
* Types of charges to be moved.
|
||||
@@ -423,11 +244,6 @@ enum res_type {
|
||||
*/
|
||||
static DEFINE_MUTEX(memcg_create_mutex);
|
||||
|
||||
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
|
||||
{
|
||||
return s ? container_of(s, struct mem_cgroup, css) : NULL;
|
||||
}
|
||||
|
||||
/* Some nice accessors for the vmpressure. */
|
||||
struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
|
||||
{
|
||||
@@ -593,11 +409,6 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
|
||||
return &memcg->nodeinfo[nid]->zoneinfo[zid];
|
||||
}
|
||||
|
||||
struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
|
||||
{
|
||||
return &memcg->css;
|
||||
}
|
||||
|
||||
/**
|
||||
* mem_cgroup_css_from_page - css of the memcg associated with a page
|
||||
* @page: page of interest
|
||||
@@ -876,14 +687,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
|
||||
__this_cpu_add(memcg->stat->nr_page_events, nr_pages);
|
||||
}
|
||||
|
||||
unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
|
||||
{
|
||||
struct mem_cgroup_per_zone *mz;
|
||||
|
||||
mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
|
||||
return mz->lru_size[lru];
|
||||
}
|
||||
|
||||
static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
|
||||
int nid,
|
||||
unsigned int lru_mask)
|
||||
@@ -986,6 +789,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
|
||||
|
||||
return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
|
||||
}
|
||||
EXPORT_SYMBOL(mem_cgroup_from_task);
|
||||
|
||||
static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
|
||||
{
|
||||
@@ -1031,7 +835,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
|
||||
struct mem_cgroup *prev,
|
||||
struct mem_cgroup_reclaim_cookie *reclaim)
|
||||
{
|
||||
struct reclaim_iter *uninitialized_var(iter);
|
||||
struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
|
||||
struct cgroup_subsys_state *css = NULL;
|
||||
struct mem_cgroup *memcg = NULL;
|
||||
struct mem_cgroup *pos = NULL;
|
||||
@@ -1173,30 +977,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
|
||||
iter != NULL; \
|
||||
iter = mem_cgroup_iter(NULL, iter, NULL))
|
||||
|
||||
void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
|
||||
{
|
||||
struct mem_cgroup *memcg;
|
||||
|
||||
rcu_read_lock();
|
||||
memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
|
||||
if (unlikely(!memcg))
|
||||
goto out;
|
||||
|
||||
switch (idx) {
|
||||
case PGFAULT:
|
||||
this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
|
||||
break;
|
||||
case PGMAJFAULT:
|
||||
this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
|
||||
break;
|
||||
default:
|
||||
BUG();
|
||||
}
|
||||
out:
|
||||
rcu_read_unlock();
|
||||
}
|
||||
EXPORT_SYMBOL(__mem_cgroup_count_vm_event);
|
||||
|
||||
/**
|
||||
* mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
|
||||
* @zone: zone of the wanted lruvec
|
||||
@@ -1295,15 +1075,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
|
||||
VM_BUG_ON((long)(*lru_size) < 0);
|
||||
}
|
||||
|
||||
bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root)
|
||||
{
|
||||
if (root == memcg)
|
||||
return true;
|
||||
if (!root->use_hierarchy)
|
||||
return false;
|
||||
return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
|
||||
}
|
||||
|
||||
bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
|
||||
{
|
||||
struct mem_cgroup *task_memcg;
|
||||
@@ -1330,39 +1101,6 @@ bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
|
||||
return ret;
|
||||
}
|
||||
|
||||
int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
|
||||
{
|
||||
unsigned long inactive_ratio;
|
||||
unsigned long inactive;
|
||||
unsigned long active;
|
||||
unsigned long gb;
|
||||
|
||||
inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
|
||||
active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);
|
||||
|
||||
gb = (inactive + active) >> (30 - PAGE_SHIFT);
|
||||
if (gb)
|
||||
inactive_ratio = int_sqrt(10 * gb);
|
||||
else
|
||||
inactive_ratio = 1;
|
||||
|
||||
return inactive * inactive_ratio < active;
|
||||
}
|
||||
|
||||
bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
|
||||
{
|
||||
struct mem_cgroup_per_zone *mz;
|
||||
struct mem_cgroup *memcg;
|
||||
|
||||
if (mem_cgroup_disabled())
|
||||
return true;
|
||||
|
||||
mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
|
||||
memcg = mz->memcg;
|
||||
|
||||
return !!(memcg->css.flags & CSS_ONLINE);
|
||||
}
|
||||
|
||||
#define mem_cgroup_from_counter(counter, member) \
|
||||
container_of(counter, struct mem_cgroup, member)
|
||||
|
||||
@@ -1394,15 +1132,6 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
|
||||
return margin;
|
||||
}
|
||||
|
||||
int mem_cgroup_swappiness(struct mem_cgroup *memcg)
|
||||
{
|
||||
/* root ? */
|
||||
if (mem_cgroup_disabled() || !memcg->css.parent)
|
||||
return vm_swappiness;
|
||||
|
||||
return memcg->swappiness;
|
||||
}
|
||||
|
||||
/*
|
||||
* A routine for checking "mem" is under move_account() or not.
|
||||
*
|
||||
@@ -2067,23 +1796,6 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
|
||||
}
|
||||
EXPORT_SYMBOL(mem_cgroup_end_page_stat);
|
||||
|
||||
/**
|
||||
* mem_cgroup_update_page_stat - update page state statistics
|
||||
* @memcg: memcg to account against
|
||||
* @idx: page state item to account
|
||||
* @val: number of pages (positive or negative)
|
||||
*
|
||||
* See mem_cgroup_begin_page_stat() for locking requirements.
|
||||
*/
|
||||
void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
|
||||
enum mem_cgroup_stat_index idx, int val)
|
||||
{
|
||||
VM_BUG_ON(!rcu_read_lock_held());
|
||||
|
||||
if (memcg)
|
||||
this_cpu_add(memcg->stat->count[idx], val);
|
||||
}
|
||||
|
||||
/*
|
||||
* size of first charge trial. "32" comes from vmscan.c's magic value.
|
||||
* TODO: maybe necessary to use big numbers in big irons.
|
||||
@@ -2509,16 +2221,6 @@ void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages)
|
||||
css_put_many(&memcg->css, nr_pages);
|
||||
}
|
||||
|
||||
/*
|
||||
* helper for acessing a memcg's index. It will be used as an index in the
|
||||
* child cache array in kmem_cache, and also to derive its name. This function
|
||||
* will return -1 when this is not a kmem-limited memcg.
|
||||
*/
|
||||
int memcg_cache_id(struct mem_cgroup *memcg)
|
||||
{
|
||||
return memcg ? memcg->kmemcg_id : -1;
|
||||
}
|
||||
|
||||
static int memcg_alloc_cache_id(void)
|
||||
{
|
||||
int id, size;
|
||||
@@ -5525,19 +5227,6 @@ struct cgroup_subsys memory_cgrp_subsys = {
|
||||
.early_init = 0,
|
||||
};
|
||||
|
||||
/**
|
||||
* mem_cgroup_events - count memory events against a cgroup
|
||||
* @memcg: the memory cgroup
|
||||
* @idx: the event index
|
||||
* @nr: the number of events to account for
|
||||
*/
|
||||
void mem_cgroup_events(struct mem_cgroup *memcg,
|
||||
enum mem_cgroup_events_index idx,
|
||||
unsigned int nr)
|
||||
{
|
||||
this_cpu_add(memcg->stat->events[idx], nr);
|
||||
}
|
||||
|
||||
/**
|
||||
* mem_cgroup_low - check if memory consumption is below the normal range
|
||||
* @root: the highest ancestor to consider
|
||||
|
||||
Reference in New Issue
Block a user