Skip to content

L
linux-davinci
Commit f64c3f54 authored by Balbir Singh's avatar Balbir Singh Committed by Linus Torvalds
Browse files
Options

memory controller: soft limit organize cgroups 

Organize cgroups over soft limit in a RB-Tree

Introduce an RB-Tree for storing memory cgroups that are over their soft
limit.  The overall goal is to

1. Add a memory cgroup to the RB-Tree when the soft limit is exceeded.
   We are careful about updates, updates take place only after a particular
   time interval has passed
2. We remove the node from the RB-Tree when the usage goes below the soft
   limit

The next set of patches will exploit the RB-Tree to get the group that is
over its soft limit by the largest amount and reclaim from it, when we
face memory contention.

[hugh.dickins@tiscali.co.uk: CONFIG_CGROUP_MEM_RES_CTLR=y CONFIG_PREEMPT=y fails to boot]
Signed-off-by: default avatarBalbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: default avatarKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: default avatarHugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 296c81d8
Show whitespace changes
Inline Side-by-side
Showing with 277 additions and 47 deletions
include/linux/res_counter.h
View file @ f64c3f54
...@@ -114,7 +114,8 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent); ...@@ -114,7 +114,8 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent);
int __must_check res_counter_charge_locked(struct res_counter *counter, int __must_check res_counter_charge_locked(struct res_counter *counter,
unsigned long val); unsigned long val);
int __must_check res_counter_charge(struct res_counter *counter, int __must_check res_counter_charge(struct res_counter *counter,
unsigned long val, struct res_counter **limit_fail_at); unsigned long val, struct res_counter **limit_fail_at,
struct res_counter **soft_limit_at);
/* /*
* uncharge - tell that some portion of the resource is released * uncharge - tell that some portion of the resource is released
...@@ -127,7 +128,8 @@ int __must_check res_counter_charge(struct res_counter *counter, ...@@ -127,7 +128,8 @@ int __must_check res_counter_charge(struct res_counter *counter,
*/ */
void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
void res_counter_uncharge(struct res_counter *counter, unsigned long val); void res_counter_uncharge(struct res_counter *counter, unsigned long val,
bool *was_soft_limit_excess);
static inline bool res_counter_limit_check_locked(struct res_counter *cnt) static inline bool res_counter_limit_check_locked(struct res_counter *cnt)
{ {
......
kernel/res_counter.c
View file @ f64c3f54
...@@ -37,17 +37,27 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val) ...@@ -37,17 +37,27 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
} }
int res_counter_charge(struct res_counter *counter, unsigned long val, int res_counter_charge(struct res_counter *counter, unsigned long val,
struct res_counter **limit_fail_at) struct res_counter **limit_fail_at,
struct res_counter **soft_limit_fail_at)
{ {
int ret; int ret;
unsigned long flags; unsigned long flags;
struct res_counter *c, *u; struct res_counter *c, *u;
*limit_fail_at = NULL; *limit_fail_at = NULL;
if (soft_limit_fail_at)
*soft_limit_fail_at = NULL;
local_irq_save(flags); local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) { for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock); spin_lock(&c->lock);
ret = res_counter_charge_locked(c, val); ret = res_counter_charge_locked(c, val);
/*
* With soft limits, we return the highest ancestor
* that exceeds its soft limit
*/
if (soft_limit_fail_at &&
!res_counter_soft_limit_check_locked(c))
*soft_limit_fail_at = c;
spin_unlock(&c->lock); spin_unlock(&c->lock);
if (ret < 0) { if (ret < 0) {
*limit_fail_at = c; *limit_fail_at = c;
...@@ -75,7 +85,8 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) ...@@ -75,7 +85,8 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
counter->usage -= val; counter->usage -= val;
} }
void res_counter_uncharge(struct res_counter *counter, unsigned long val) void res_counter_uncharge(struct res_counter *counter, unsigned long val,
bool *was_soft_limit_excess)
{ {
unsigned long flags; unsigned long flags;
struct res_counter *c; struct res_counter *c;
...@@ -83,6 +94,9 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val) ...@@ -83,6 +94,9 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val)
local_irq_save(flags); local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) { for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock); spin_lock(&c->lock);
if (was_soft_limit_excess)
*was_soft_limit_excess =
!res_counter_soft_limit_check_locked(c);
res_counter_uncharge_locked(c, val); res_counter_uncharge_locked(c, val);
spin_unlock(&c->lock); spin_unlock(&c->lock);
} }
......
mm/memcontrol.c
View file @ f64c3f54
...@@ -29,6 +29,7 @@ ...@@ -29,6 +29,7 @@
#include <linux/rcupdate.h> #include <linux/rcupdate.h>
#include <linux/limits.h> #include <linux/limits.h>
#include <linux/mutex.h> #include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/swap.h> #include <linux/swap.h>
#include <linux/spinlock.h> #include <linux/spinlock.h>
...@@ -54,6 +55,7 @@ static int really_do_swap_account __initdata = 1; /* for remember boot option*/ ...@@ -54,6 +55,7 @@ static int really_do_swap_account __initdata = 1; /* for remember boot option*/
#endif #endif
static DEFINE_MUTEX(memcg_tasklist); /* can be hold under cgroup_mutex */ static DEFINE_MUTEX(memcg_tasklist); /* can be hold under cgroup_mutex */
#define SOFTLIMIT_EVENTS_THRESH (1000)
/* /*
* Statistics for memory cgroup. * Statistics for memory cgroup.
...@@ -67,6 +69,7 @@ enum mem_cgroup_stat_index { ...@@ -67,6 +69,7 @@ enum mem_cgroup_stat_index {
MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */ MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */
MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */ MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */ MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
MEM_CGROUP_STAT_EVENTS, /* sum of pagein + pageout for internal use */
MEM_CGROUP_STAT_NSTATS, MEM_CGROUP_STAT_NSTATS,
}; };
...@@ -79,6 +82,20 @@ struct mem_cgroup_stat { ...@@ -79,6 +82,20 @@ struct mem_cgroup_stat {
struct mem_cgroup_stat_cpu cpustat[0]; struct mem_cgroup_stat_cpu cpustat[0];
}; };
static inline void
__mem_cgroup_stat_reset_safe(struct mem_cgroup_stat_cpu *stat,
enum mem_cgroup_stat_index idx)
{
stat->count[idx] = 0;
}
static inline s64
__mem_cgroup_stat_read_local(struct mem_cgroup_stat_cpu *stat,
enum mem_cgroup_stat_index idx)
{
return stat->count[idx];
}
/* /*
* For accounting under irq disable, no need for increment preempt count. * For accounting under irq disable, no need for increment preempt count.
*/ */
...@@ -118,6 +135,10 @@ struct mem_cgroup_per_zone { ...@@ -118,6 +135,10 @@ struct mem_cgroup_per_zone {
unsigned long count[NR_LRU_LISTS]; unsigned long count[NR_LRU_LISTS];
struct zone_reclaim_stat reclaim_stat; struct zone_reclaim_stat reclaim_stat;
struct rb_node tree_node; /* RB tree node */
unsigned long long usage_in_excess;/* Set to the value by which */
/* the soft limit is exceeded*/
bool on_tree;
}; };
/* Macro for accessing counter */ /* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)]) #define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)])
...@@ -130,6 +151,26 @@ struct mem_cgroup_lru_info { ...@@ -130,6 +151,26 @@ struct mem_cgroup_lru_info {
struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES]; struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
}; };
/*
* Cgroups above their limits are maintained in a RB-Tree, independent of
* their hierarchy representation
*/
struct mem_cgroup_tree_per_zone {
struct rb_root rb_root;
spinlock_t lock;
};
struct mem_cgroup_tree_per_node {
struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
};
struct mem_cgroup_tree {
struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
};
static struct mem_cgroup_tree soft_limit_tree __read_mostly;
/* /*
* The memory controller data structure. The memory controller controls both * The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide * page cache and RSS per cgroup. We would eventually like to provide
...@@ -215,6 +256,150 @@ static void mem_cgroup_get(struct mem_cgroup *mem); ...@@ -215,6 +256,150 @@ static void mem_cgroup_get(struct mem_cgroup *mem);
static void mem_cgroup_put(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem);
static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}
static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
struct mem_cgroup *mem = pc->mem_cgroup;
int nid = page_cgroup_nid(pc);
int zid = page_cgroup_zid(pc);
if (!mem)
return NULL;
return mem_cgroup_zoneinfo(mem, nid, zid);
}
static struct mem_cgroup_tree_per_zone *
soft_limit_tree_node_zone(int nid, int zid)
{
return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
}
static struct mem_cgroup_tree_per_zone *
soft_limit_tree_from_page(struct page *page)
{
int nid = page_to_nid(page);
int zid = page_zonenum(page);
return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
}
static void
mem_cgroup_insert_exceeded(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
struct mem_cgroup_tree_per_zone *mctz)
{
struct rb_node **p = &mctz->rb_root.rb_node;
struct rb_node *parent = NULL;
struct mem_cgroup_per_zone *mz_node;
if (mz->on_tree)
return;
mz->usage_in_excess = res_counter_soft_limit_excess(&mem->res);
spin_lock(&mctz->lock);
while (*p) {
parent = *p;
mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
tree_node);
if (mz->usage_in_excess < mz_node->usage_in_excess)
p = &(*p)->rb_left;
/*
* We can't avoid mem cgroups that are over their soft
* limit by the same amount
*/
else if (mz->usage_in_excess >= mz_node->usage_in_excess)
p = &(*p)->rb_right;
}
rb_link_node(&mz->tree_node, parent, p);
rb_insert_color(&mz->tree_node, &mctz->rb_root);
mz->on_tree = true;
spin_unlock(&mctz->lock);
}
static void
mem_cgroup_remove_exceeded(struct mem_cgroup *mem,
struct mem_cgroup_per_zone *mz,
struct mem_cgroup_tree_per_zone *mctz)
{
spin_lock(&mctz->lock);
rb_erase(&mz->tree_node, &mctz->rb_root);
mz->on_tree = false;
spin_unlock(&mctz->lock);
}
static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem)
{
bool ret = false;
int cpu;
s64 val;
struct mem_cgroup_stat_cpu *cpustat;
cpu = get_cpu();
cpustat = &mem->stat.cpustat[cpu];
val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_EVENTS);
if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) {
__mem_cgroup_stat_reset_safe(cpustat, MEM_CGROUP_STAT_EVENTS);
ret = true;
}
put_cpu();
return ret;
}
static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page)
{
unsigned long long prev_usage_in_excess, new_usage_in_excess;
bool updated_tree = false;
struct mem_cgroup_per_zone *mz;
struct mem_cgroup_tree_per_zone *mctz;
mz = mem_cgroup_zoneinfo(mem, page_to_nid(page), page_zonenum(page));
mctz = soft_limit_tree_from_page(page);
/*
* We do updates in lazy mode, mem's are removed
* lazily from the per-zone, per-node rb tree
*/
prev_usage_in_excess = mz->usage_in_excess;
new_usage_in_excess = res_counter_soft_limit_excess(&mem->res);
if (prev_usage_in_excess) {
mem_cgroup_remove_exceeded(mem, mz, mctz);
updated_tree = true;
}
if (!new_usage_in_excess)
goto done;
mem_cgroup_insert_exceeded(mem, mz, mctz);
done:
if (updated_tree) {
spin_lock(&mctz->lock);
mz->usage_in_excess = new_usage_in_excess;
spin_unlock(&mctz->lock);
}
}
static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem)
{
int node, zone;
struct mem_cgroup_per_zone *mz;
struct mem_cgroup_tree_per_zone *mctz;
for_each_node_state(node, N_POSSIBLE) {
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
mz = mem_cgroup_zoneinfo(mem, node, zone);
mctz = soft_limit_tree_node_zone(node, zone);
mem_cgroup_remove_exceeded(mem, mz, mctz);
}
}
}
static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
struct page_cgroup *pc, struct page_cgroup *pc,
bool charge) bool charge)
...@@ -236,28 +421,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, ...@@ -236,28 +421,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
else else
__mem_cgroup_stat_add_safe(cpustat, __mem_cgroup_stat_add_safe(cpustat,
MEM_CGROUP_STAT_PGPGOUT_COUNT, 1); MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1);
put_cpu(); put_cpu();
} }
static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}
static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
struct mem_cgroup *mem = pc->mem_cgroup;
int nid = page_cgroup_nid(pc);
int zid = page_cgroup_zid(pc);
if (!mem)
return NULL;
return mem_cgroup_zoneinfo(mem, nid, zid);
}
static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem, static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem,
enum lru_list idx) enum lru_list idx)
{ {
...@@ -972,11 +1139,11 @@ done: ...@@ -972,11 +1139,11 @@ done:
*/ */
static int __mem_cgroup_try_charge(struct mm_struct *mm, static int __mem_cgroup_try_charge(struct mm_struct *mm,
gfp_t gfp_mask, struct mem_cgroup **memcg, gfp_t gfp_mask, struct mem_cgroup **memcg,
bool oom) bool oom, struct page *page)
{ {
struct mem_cgroup *mem, *mem_over_limit; struct mem_cgroup *mem, *mem_over_limit, *mem_over_soft_limit;
int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
struct res_counter *fail_res; struct res_counter *fail_res, *soft_fail_res = NULL;
if (unlikely(test_thread_flag(TIF_MEMDIE))) { if (unlikely(test_thread_flag(TIF_MEMDIE))) {
/* Don't account this! */ /* Don't account this! */
...@@ -1006,16 +1173,17 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, ...@@ -1006,16 +1173,17 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
int ret; int ret;
bool noswap = false; bool noswap = false;
ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res,
&soft_fail_res);
if (likely(!ret)) { if (likely(!ret)) {
if (!do_swap_account) if (!do_swap_account)
break; break;
ret = res_counter_charge(&mem->memsw, PAGE_SIZE, ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
&fail_res); &fail_res, NULL);
if (likely(!ret)) if (likely(!ret))
break; break;
/* mem+swap counter fails */ /* mem+swap counter fails */
res_counter_uncharge(&mem->res, PAGE_SIZE); res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
noswap = true; noswap = true;
mem_over_limit = mem_cgroup_from_res_counter(fail_res, mem_over_limit = mem_cgroup_from_res_counter(fail_res,
memsw); memsw);
...@@ -1053,13 +1221,23 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, ...@@ -1053,13 +1221,23 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
goto nomem; goto nomem;
} }
} }
/*
* Insert just the ancestor, we should trickle down to the correct
* cgroup for reclaim, since the other nodes will be below their
* soft limit
*/
if (soft_fail_res) {
mem_over_soft_limit =
mem_cgroup_from_res_counter(soft_fail_res, res);
if (mem_cgroup_soft_limit_check(mem_over_soft_limit))
mem_cgroup_update_tree(mem_over_soft_limit, page);
}
return 0; return 0;
nomem: nomem:
css_put(&mem->css); css_put(&mem->css);
return -ENOMEM; return -ENOMEM;
} }
/* /*
* A helper function to get mem_cgroup from ID. must be called under * A helper function to get mem_cgroup from ID. must be called under
* rcu_read_lock(). The caller must check css_is_removed() or some if * rcu_read_lock(). The caller must check css_is_removed() or some if
...@@ -1126,9 +1304,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem, ...@@ -1126,9 +1304,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
lock_page_cgroup(pc); lock_page_cgroup(pc);
if (unlikely(PageCgroupUsed(pc))) { if (unlikely(PageCgroupUsed(pc))) {
unlock_page_cgroup(pc); unlock_page_cgroup(pc);
res_counter_uncharge(&mem->res, PAGE_SIZE); res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
if (do_swap_account) if (do_swap_account)
res_counter_uncharge(&mem->memsw, PAGE_SIZE); res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
css_put(&mem->css); css_put(&mem->css);
return; return;
} }
...@@ -1205,7 +1383,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, ...@@ -1205,7 +1383,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
if (pc->mem_cgroup != from) if (pc->mem_cgroup != from)
goto out; goto out;
res_counter_uncharge(&from->res, PAGE_SIZE); res_counter_uncharge(&from->res, PAGE_SIZE, NULL);
mem_cgroup_charge_statistics(from, pc, false); mem_cgroup_charge_statistics(from, pc, false);
page = pc->page; page = pc->page;
...@@ -1225,7 +1403,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc, ...@@ -1225,7 +1403,7 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
} }
if (do_swap_account) if (do_swap_account)
res_counter_uncharge(&from->memsw, PAGE_SIZE); res_counter_uncharge(&from->memsw, PAGE_SIZE, NULL);
css_put(&from->css); css_put(&from->css);
css_get(&to->css); css_get(&to->css);
...@@ -1265,7 +1443,7 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc, ...@@ -1265,7 +1443,7 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
parent = mem_cgroup_from_cont(pcg); parent = mem_cgroup_from_cont(pcg);
ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false); ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page);
if (ret || !parent) if (ret || !parent)
return ret; return ret;
...@@ -1295,9 +1473,9 @@ uncharge: ...@@ -1295,9 +1473,9 @@ uncharge:
/* drop extra refcnt by try_charge() */ /* drop extra refcnt by try_charge() */
css_put(&parent->css); css_put(&parent->css);
/* uncharge if move fails */ /* uncharge if move fails */
res_counter_uncharge(&parent->res, PAGE_SIZE); res_counter_uncharge(&parent->res, PAGE_SIZE, NULL);
if (do_swap_account) if (do_swap_account)
res_counter_uncharge(&parent->memsw, PAGE_SIZE); res_counter_uncharge(&parent->memsw, PAGE_SIZE, NULL);
return ret; return ret;
} }
...@@ -1322,7 +1500,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, ...@@ -1322,7 +1500,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
prefetchw(pc); prefetchw(pc);
mem = memcg; mem = memcg;
ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true); ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page);
if (ret || !mem) if (ret || !mem)
return ret; return ret;
...@@ -1441,14 +1619,14 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm, ...@@ -1441,14 +1619,14 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
if (!mem) if (!mem)
goto charge_cur_mm; goto charge_cur_mm;
*ptr = mem; *ptr = mem;
ret = __mem_cgroup_try_charge(NULL, mask, ptr, true); ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page);
/* drop extra refcnt from tryget */ /* drop extra refcnt from tryget */
css_put(&mem->css); css_put(&mem->css);
return ret; return ret;
charge_cur_mm: charge_cur_mm:
if (unlikely(!mm)) if (unlikely(!mm))
mm = &init_mm; mm = &init_mm;
return __mem_cgroup_try_charge(mm, mask, ptr, true); return __mem_cgroup_try_charge(mm, mask, ptr, true, page);
} }
static void static void
...@@ -1486,7 +1664,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, ...@@ -1486,7 +1664,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
* This recorded memcg can be obsolete one. So, avoid * This recorded memcg can be obsolete one. So, avoid
* calling css_tryget * calling css_tryget
*/ */
res_counter_uncharge(&memcg->memsw, PAGE_SIZE); res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL);
mem_cgroup_put(memcg); mem_cgroup_put(memcg);
} }
rcu_read_unlock(); rcu_read_unlock();
...@@ -1511,9 +1689,9 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem) ...@@ -1511,9 +1689,9 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
return; return;
if (!mem) if (!mem)
return; return;
res_counter_uncharge(&mem->res, PAGE_SIZE); res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
if (do_swap_account) if (do_swap_account)
res_counter_uncharge(&mem->memsw, PAGE_SIZE); res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
css_put(&mem->css); css_put(&mem->css);
} }
...@@ -1527,6 +1705,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) ...@@ -1527,6 +1705,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
struct page_cgroup *pc; struct page_cgroup *pc;
struct mem_cgroup *mem = NULL; struct mem_cgroup *mem = NULL;
struct mem_cgroup_per_zone *mz; struct mem_cgroup_per_zone *mz;
bool soft_limit_excess = false;
if (mem_cgroup_disabled()) if (mem_cgroup_disabled())
return NULL; return NULL;
...@@ -1565,9 +1744,9 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) ...@@ -1565,9 +1744,9 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
break; break;
} }
res_counter_uncharge(&mem->res, PAGE_SIZE); res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess);
if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)) if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
res_counter_uncharge(&mem->memsw, PAGE_SIZE); res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
mem_cgroup_charge_statistics(mem, pc, false); mem_cgroup_charge_statistics(mem, pc, false);
ClearPageCgroupUsed(pc); ClearPageCgroupUsed(pc);
...@@ -1581,6 +1760,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) ...@@ -1581,6 +1760,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
mz = page_cgroup_zoneinfo(pc); mz = page_cgroup_zoneinfo(pc);
unlock_page_cgroup(pc); unlock_page_cgroup(pc);
if (soft_limit_excess && mem_cgroup_soft_limit_check(mem))
mem_cgroup_update_tree(mem, page);
/* at swapout, this memcg will be accessed to record to swap */ /* at swapout, this memcg will be accessed to record to swap */
if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT) if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
css_put(&mem->css); css_put(&mem->css);
...@@ -1656,7 +1837,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent) ...@@ -1656,7 +1837,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent)
* We uncharge this because swap is freed. * We uncharge this because swap is freed.
* This memcg can be obsolete one. We avoid calling css_tryget * This memcg can be obsolete one. We avoid calling css_tryget
*/ */
res_counter_uncharge(&memcg->memsw, PAGE_SIZE); res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL);
mem_cgroup_put(memcg); mem_cgroup_put(memcg);
} }
rcu_read_unlock(); rcu_read_unlock();
...@@ -1685,7 +1866,8 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) ...@@ -1685,7 +1866,8 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
unlock_page_cgroup(pc); unlock_page_cgroup(pc);
if (mem) { if (mem) {
ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false); ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false,
page);
css_put(&mem->css); css_put(&mem->css);
} }
*ptr = mem; *ptr = mem;
...@@ -2194,6 +2376,7 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) ...@@ -2194,6 +2376,7 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
res_counter_reset_failcnt(&mem->memsw); res_counter_reset_failcnt(&mem->memsw);
break; break;
} }
return 0; return 0;
} }
...@@ -2489,6 +2672,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node) ...@@ -2489,6 +2672,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
mz = &pn->zoneinfo[zone]; mz = &pn->zoneinfo[zone];
for_each_lru(l) for_each_lru(l)
INIT_LIST_HEAD(&mz->lists[l]); INIT_LIST_HEAD(&mz->lists[l]);
mz->usage_in_excess = 0;
} }
return 0; return 0;
} }
...@@ -2534,6 +2718,7 @@ static void __mem_cgroup_free(struct mem_cgroup *mem) ...@@ -2534,6 +2718,7 @@ static void __mem_cgroup_free(struct mem_cgroup *mem)
{ {
int node; int node;
mem_cgroup_remove_from_trees(mem);
free_css_id(&mem_cgroup_subsys, &mem->css); free_css_id(&mem_cgroup_subsys, &mem->css);
for_each_node_state(node, N_POSSIBLE) for_each_node_state(node, N_POSSIBLE)
...@@ -2582,6 +2767,31 @@ static void __init enable_swap_cgroup(void) ...@@ -2582,6 +2767,31 @@ static void __init enable_swap_cgroup(void)
} }
#endif #endif
static int mem_cgroup_soft_limit_tree_init(void)
{
struct mem_cgroup_tree_per_node *rtpn;
struct mem_cgroup_tree_per_zone *rtpz;
int tmp, node, zone;
for_each_node_state(node, N_POSSIBLE) {
tmp = node;
if (!node_state(node, N_NORMAL_MEMORY))
tmp = -1;
rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
if (!rtpn)
return 1;
soft_limit_tree.rb_tree_per_node[node] = rtpn;
for (zone = 0; zone < MAX_NR_ZONES; zone++) {
rtpz = &rtpn->rb_tree_per_zone[zone];
rtpz->rb_root = RB_ROOT;
spin_lock_init(&rtpz->lock);
}
}
return 0;
}
static struct cgroup_subsys_state * __ref static struct cgroup_subsys_state * __ref
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{ {
...@@ -2596,11 +2806,15 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) ...@@ -2596,11 +2806,15 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
for_each_node_state(node, N_POSSIBLE) for_each_node_state(node, N_POSSIBLE)
if (alloc_mem_cgroup_per_zone_info(mem, node)) if (alloc_mem_cgroup_per_zone_info(mem, node))
goto free_out; goto free_out;
/* root ? */ /* root ? */
if (cont->parent == NULL) { if (cont->parent == NULL) {
enable_swap_cgroup(); enable_swap_cgroup();
parent = NULL; parent = NULL;
root_mem_cgroup = mem; root_mem_cgroup = mem;
if (mem_cgroup_soft_limit_tree_init())
goto free_out;
} else { } else {
parent = mem_cgroup_from_cont(cont->parent); parent = mem_cgroup_from_cont(cont->parent);
mem->use_hierarchy = parent->use_hierarchy; mem->use_hierarchy = parent->use_hierarchy;
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment