The patch titled
memory controller: soft limit organize cgroups
has been added to the -mm tree. Its filename is
memory-controller-soft-limit-organize-cgroups-v9.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: memory controller: soft limit organize cgroups
From: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
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.
Signed-off-by: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/res_counter.h | 6
kernel/res_counter.c | 18 +-
mm/memcontrol.c | 302 +++++++++++++++++++++++++++++-----
3 files changed, 279 insertions(+), 47 deletions(-)
diff -puN include/linux/res_counter.h~memory-controller-soft-limit-organize-cgroups-v9 include/linux/res_counter.h
--- a/include/linux/res_counter.h~memory-controller-soft-limit-organize-cgroups-v9
+++ a/include/linux/res_counter.h
@@ -114,7 +114,8 @@ void res_counter_init(struct res_counter
int __must_check res_counter_charge_locked(struct res_counter *counter,
unsigned long val);
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
@@ -127,7 +128,8 @@ int __must_check res_counter_charge(stru
*/
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)
{
diff -puN kernel/res_counter.c~memory-controller-soft-limit-organize-cgroups-v9 kernel/res_counter.c
--- a/kernel/res_counter.c~memory-controller-soft-limit-organize-cgroups-v9
+++ a/kernel/res_counter.c
@@ -37,17 +37,27 @@ int res_counter_charge_locked(struct res
}
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;
unsigned long flags;
struct res_counter *c, *u;
*limit_fail_at = NULL;
+ if (soft_limit_fail_at)
+ *soft_limit_fail_at = NULL;
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock);
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);
if (ret < 0) {
*limit_fail_at = c;
@@ -75,7 +85,8 @@ void res_counter_uncharge_locked(struct
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;
struct res_counter *c;
@@ -83,6 +94,9 @@ void res_counter_uncharge(struct res_cou
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
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);
spin_unlock(&c->lock);
}
diff -puN mm/memcontrol.c~memory-controller-soft-limit-organize-cgroups-v9 mm/memcontrol.c
--- a/mm/memcontrol.c~memory-controller-soft-limit-organize-cgroups-v9
+++ a/mm/memcontrol.c
@@ -29,6 +29,7 @@
#include <linux/rcupdate.h>
#include <linux/limits.h>
#include <linux/mutex.h>
+#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
@@ -54,6 +55,7 @@ static int really_do_swap_account __init
#endif
static DEFINE_MUTEX(memcg_tasklist); /* can be hold under cgroup_mutex */
+#define SOFTLIMIT_EVENTS_THRESH (1000)
/*
* Statistics for memory cgroup.
@@ -67,6 +69,7 @@ enum mem_cgroup_stat_index {
MEM_CGROUP_STAT_MAPPED_FILE, /* # of pages charged as file rss */
MEM_CGROUP_STAT_PGPGIN_COUNT, /* # of pages paged in */
MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
+ MEM_CGROUP_STAT_EVENTS, /* sum of pagein + pageout for internal use */
MEM_CGROUP_STAT_NSTATS,
};
@@ -79,6 +82,20 @@ struct mem_cgroup_stat {
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.
*/
@@ -118,6 +135,10 @@ struct mem_cgroup_per_zone {
unsigned long count[NR_LRU_LISTS];
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 */
#define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)])
@@ -131,6 +152,26 @@ struct mem_cgroup_lru_info {
};
/*
+ * 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
* 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,
@@ -215,6 +256,152 @@ static void mem_cgroup_get(struct mem_cg
static void mem_cgroup_put(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 over_soft_limit)
+{
+ bool ret = false;
+ int cpu = get_cpu();
+ s64 val;
+ struct mem_cgroup_stat_cpu *cpustat;
+
+ if (!over_soft_limit)
+ return ret;
+
+ 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;
+ }
+ 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,
struct page_cgroup *pc,
bool charge)
@@ -236,28 +423,10 @@ static void mem_cgroup_charge_statistics
else
__mem_cgroup_stat_add_safe(cpustat,
MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
+ __mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1);
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,
enum lru_list idx)
{
@@ -972,11 +1141,11 @@ done:
*/
static int __mem_cgroup_try_charge(struct mm_struct *mm,
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;
- struct res_counter *fail_res;
+ struct res_counter *fail_res, *soft_fail_res = NULL;
if (unlikely(test_thread_flag(TIF_MEMDIE))) {
/* Don't account this! */
@@ -1006,16 +1175,17 @@ static int __mem_cgroup_try_charge(struc
int ret;
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 (!do_swap_account)
break;
ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
- &fail_res);
+ &fail_res, NULL);
if (likely(!ret))
break;
/* mem+swap counter fails */
- res_counter_uncharge(&mem->res, PAGE_SIZE);
+ res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
noswap = true;
mem_over_limit = mem_cgroup_from_res_counter(fail_res,
memsw);
@@ -1053,13 +1223,23 @@ static int __mem_cgroup_try_charge(struc
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, true))
+ mem_cgroup_update_tree(mem_over_soft_limit, page);
+ }
return 0;
nomem:
css_put(&mem->css);
return -ENOMEM;
}
-
/*
* 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
@@ -1126,9 +1306,9 @@ static void __mem_cgroup_commit_charge(s
lock_page_cgroup(pc);
if (unlikely(PageCgroupUsed(pc))) {
unlock_page_cgroup(pc);
- res_counter_uncharge(&mem->res, PAGE_SIZE);
+ res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
if (do_swap_account)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
css_put(&mem->css);
return;
}
@@ -1205,7 +1385,7 @@ static int mem_cgroup_move_account(struc
if (pc->mem_cgroup != from)
goto out;
- res_counter_uncharge(&from->res, PAGE_SIZE);
+ res_counter_uncharge(&from->res, PAGE_SIZE, NULL);
mem_cgroup_charge_statistics(from, pc, false);
page = pc->page;
@@ -1225,7 +1405,7 @@ static int mem_cgroup_move_account(struc
}
if (do_swap_account)
- res_counter_uncharge(&from->memsw, PAGE_SIZE);
+ res_counter_uncharge(&from->memsw, PAGE_SIZE, NULL);
css_put(&from->css);
css_get(&to->css);
@@ -1265,7 +1445,7 @@ static int mem_cgroup_move_parent(struct
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)
return ret;
@@ -1295,9 +1475,9 @@ uncharge:
/* drop extra refcnt by try_charge() */
css_put(&parent->css);
/* uncharge if move fails */
- res_counter_uncharge(&parent->res, PAGE_SIZE);
+ res_counter_uncharge(&parent->res, PAGE_SIZE, NULL);
if (do_swap_account)
- res_counter_uncharge(&parent->memsw, PAGE_SIZE);
+ res_counter_uncharge(&parent->memsw, PAGE_SIZE, NULL);
return ret;
}
@@ -1322,7 +1502,7 @@ static int mem_cgroup_charge_common(stru
prefetchw(pc);
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)
return ret;
@@ -1441,14 +1621,14 @@ int mem_cgroup_try_charge_swapin(struct
if (!mem)
goto charge_cur_mm;
*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 */
css_put(&mem->css);
return ret;
charge_cur_mm:
if (unlikely(!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
@@ -1486,7 +1666,7 @@ __mem_cgroup_commit_charge_swapin(struct
* This recorded memcg can be obsolete one. So, avoid
* calling css_tryget
*/
- res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+ res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL);
mem_cgroup_put(memcg);
}
rcu_read_unlock();
@@ -1511,9 +1691,9 @@ void mem_cgroup_cancel_charge_swapin(str
return;
if (!mem)
return;
- res_counter_uncharge(&mem->res, PAGE_SIZE);
+ res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
if (do_swap_account)
- res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
css_put(&mem->css);
}
@@ -1527,6 +1707,7 @@ __mem_cgroup_uncharge_common(struct page
struct page_cgroup *pc;
struct mem_cgroup *mem = NULL;
struct mem_cgroup_per_zone *mz;
+ bool soft_limit_excess = false;
if (mem_cgroup_disabled())
return NULL;
@@ -1565,9 +1746,9 @@ __mem_cgroup_uncharge_common(struct page
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))
- res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+ res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
mem_cgroup_charge_statistics(mem, pc, false);
ClearPageCgroupUsed(pc);
@@ -1581,6 +1762,8 @@ __mem_cgroup_uncharge_common(struct page
mz = page_cgroup_zoneinfo(pc);
unlock_page_cgroup(pc);
+ if (mem_cgroup_soft_limit_check(mem, soft_limit_excess))
+ mem_cgroup_update_tree(mem, page);
/* at swapout, this memcg will be accessed to record to swap */
if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
css_put(&mem->css);
@@ -1656,7 +1839,7 @@ void mem_cgroup_uncharge_swap(swp_entry_
* We uncharge this because swap is freed.
* 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);
}
rcu_read_unlock();
@@ -1685,7 +1868,8 @@ int mem_cgroup_prepare_migration(struct
unlock_page_cgroup(pc);
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);
}
*ptr = mem;
@@ -2194,6 +2378,7 @@ static int mem_cgroup_reset(struct cgrou
res_counter_reset_failcnt(&mem->memsw);
break;
}
+
return 0;
}
@@ -2489,6 +2674,7 @@ static int alloc_mem_cgroup_per_zone_inf
mz = &pn->zoneinfo[zone];
for_each_lru(l)
INIT_LIST_HEAD(&mz->lists[l]);
+ mz->usage_in_excess = 0;
}
return 0;
}
@@ -2534,6 +2720,7 @@ static void __mem_cgroup_free(struct mem
{
int node;
+ mem_cgroup_remove_from_trees(mem);
free_css_id(&mem_cgroup_subsys, &mem->css);
for_each_node_state(node, N_POSSIBLE)
@@ -2582,6 +2769,31 @@ static void __init enable_swap_cgroup(vo
}
#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
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
@@ -2596,11 +2808,15 @@ mem_cgroup_create(struct cgroup_subsys *
for_each_node_state(node, N_POSSIBLE)
if (alloc_mem_cgroup_per_zone_info(mem, node))
goto free_out;
+
/* root ? */
if (cont->parent == NULL) {
enable_swap_cgroup();
parent = NULL;
root_mem_cgroup = mem;
+ if (mem_cgroup_soft_limit_tree_init())
+ goto free_out;
+
} else {
parent = mem_cgroup_from_cont(cont->parent);
mem->use_hierarchy = parent->use_hierarchy;
_
Patches currently in -mm which might be from balbir@xxxxxxxxxxxxxxxxxx are
linux-next.patch
cgroup-avoid-permanent-sleep-at-rmdir-v7.patch
memcg-remove-the-overhead-associated-with-the-root-cgroup.patch
memcg-remove-the-overhead-associated-with-the-root-cgroup-fix.patch
memcg-remove-the-overhead-associated-with-the-root-cgroup-fix-2.patch
memcg-add-comments-explaining-memory-barriers.patch
memory-controller-soft-limit-documentation-v9.patch
memory-controller-soft-limit-interface-v9.patch
memory-controller-soft-limit-organize-cgroups-v9.patch
memory-controller-soft-limit-refactor-reclaim-flags-v9.patch
memory-controller-soft-limit-reclaim-on-contention-v9.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
