| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20100825170741.f1f0a220.kamezawa.hiroyu@jp.fujitsu.com>
Date: Wed, 25 Aug 2010 17:07:41 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc: linux-mm@...ck.org,
"nishimura@....nes.nec.co.jp" <nishimura@....nes.nec.co.jp>,
"balbir@...ux.vnet.ibm.com" <balbir@...ux.vnet.ibm.com>,
gthelen@...gle.com, m-ikeda@...jp.nec.com,
"akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"menage@...gle.com" <menage@...gle.com>,
"lizf@...fujitsu.com" <lizf@...fujitsu.com>
Subject: [PATCH 2/5] memcg: quick memcg lookup array
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Now, memory cgroup has an ID per cgroup and make use of it at
- hierarchy walk,
- swap recording.
This patch is for making more use of it. The final purpose is
to replace page_cgroup->mem_cgroup's pointer to an unsigned short.
This patch caches a pointer of memcg in an array. By this, we
don't have to call css_lookup() which requires radix-hash walk.
This saves some amount of memory footprint at lookup memcg via id.
Changelog: 20100825
- applied comments.
Changelog: 20100811
- adjusted onto mmotm-2010-08-11
- fixed RCU related parts.
- use attach_id() callback.
Changelog: 20100804
- fixed description in init/Kconfig
Changelog: 20100730
- fixed rcu_read_unlock() placement.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
---
init/Kconfig | 10 +++++++
mm/memcontrol.c | 75 +++++++++++++++++++++++++++++++++++++++++---------------
2 files changed, 65 insertions(+), 20 deletions(-)
Index: mmotm-0811/mm/memcontrol.c
===================================================================
--- mmotm-0811.orig/mm/memcontrol.c
+++ mmotm-0811/mm/memcontrol.c
@@ -195,6 +195,7 @@ static void mem_cgroup_oom_notify(struct
*/
struct mem_cgroup {
struct cgroup_subsys_state css;
+ int valid; /* for checking validness under RCU access.*/
/*
* the counter to account for memory usage
*/
@@ -294,6 +295,29 @@ static bool move_file(void)
&mc.to->move_charge_at_immigrate);
}
+/* 0 is unused */
+static atomic_t mem_cgroup_num;
+#define NR_MEMCG_GROUPS (CONFIG_MEM_CGROUP_MAX_GROUPS + 1)
+static struct mem_cgroup *mem_cgroups[NR_MEMCG_GROUPS] __read_mostly;
+
+/* Must be called under rcu_read_lock */
+static struct mem_cgroup *id_to_memcg(unsigned short id)
+{
+ struct mem_cgroup *mem;
+ /* see mem_cgroup_free() */
+ mem = rcu_dereference_check(mem_cgroups[id], rcu_read_lock_held());
+ if (likely(mem && mem->valid))
+ return mem;
+ return NULL;
+}
+
+static void register_memcg_id(struct mem_cgroup *mem)
+{
+ int id = css_id(&mem->css);
+ rcu_assign_pointer(mem_cgroups[id], mem);
+ VM_BUG_ON(!mem->valid);
+}
+
/*
* Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft
* limit reclaim to prevent infinite loops, if they ever occur.
@@ -1847,18 +1871,7 @@ static void mem_cgroup_cancel_charge(str
* it's concern. (dropping refcnt from swap can be called against removed
* memcg.)
*/
-static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
-{
- struct cgroup_subsys_state *css;
- /* ID 0 is unused ID */
- if (!id)
- return NULL;
- css = css_lookup(&mem_cgroup_subsys, id);
- if (!css)
- return NULL;
- return container_of(css, struct mem_cgroup, css);
-}
struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
{
@@ -1879,7 +1892,7 @@ struct mem_cgroup *try_get_mem_cgroup_fr
ent.val = page_private(page);
id = lookup_swap_cgroup(ent);
rcu_read_lock();
- mem = mem_cgroup_lookup(id);
+ mem = id_to_memcg(id);
if (mem && !css_tryget(&mem->css))
mem = NULL;
rcu_read_unlock();
@@ -2231,7 +2244,7 @@ __mem_cgroup_commit_charge_swapin(struct
id = swap_cgroup_record(ent, 0);
rcu_read_lock();
- memcg = mem_cgroup_lookup(id);
+ memcg = id_to_memcg(id);
if (memcg) {
/*
* This recorded memcg can be obsolete one. So, avoid
@@ -2240,9 +2253,10 @@ __mem_cgroup_commit_charge_swapin(struct
if (!mem_cgroup_is_root(memcg))
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_swap_statistics(memcg, false);
+ rcu_read_unlock();
mem_cgroup_put(memcg);
- }
- rcu_read_unlock();
+ } else
+ rcu_read_unlock();
}
/*
* At swapin, we may charge account against cgroup which has no tasks.
@@ -2495,7 +2509,7 @@ void mem_cgroup_uncharge_swap(swp_entry_
id = swap_cgroup_record(ent, 0);
rcu_read_lock();
- memcg = mem_cgroup_lookup(id);
+ memcg = id_to_memcg(id);
if (memcg) {
/*
* We uncharge this because swap is freed.
@@ -2504,9 +2518,10 @@ void mem_cgroup_uncharge_swap(swp_entry_
if (!mem_cgroup_is_root(memcg))
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_swap_statistics(memcg, false);
+ rcu_read_unlock();
mem_cgroup_put(memcg);
- }
- rcu_read_unlock();
+ } else
+ rcu_read_unlock();
}
/**
@@ -4010,6 +4025,9 @@ static struct mem_cgroup *mem_cgroup_all
struct mem_cgroup *mem;
int size = sizeof(struct mem_cgroup);
+ if (atomic_read(&mem_cgroup_num) == NR_MEMCG_GROUPS)
+ return NULL;
+
/* Can be very big if MAX_NUMNODES is very big */
if (size < PAGE_SIZE)
mem = kmalloc(size, GFP_KERNEL);
@@ -4020,6 +4038,7 @@ static struct mem_cgroup *mem_cgroup_all
return NULL;
memset(mem, 0, size);
+ mem->valid = 1;
mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
if (!mem->stat) {
if (size < PAGE_SIZE)
@@ -4049,6 +4068,7 @@ static void __mem_cgroup_free(struct mem
mem_cgroup_remove_from_trees(mem);
free_css_id(&mem_cgroup_subsys, &mem->css);
+ atomic_dec(&mem_cgroup_num);
for_each_node_state(node, N_POSSIBLE)
free_mem_cgroup_per_zone_info(mem, node);
@@ -4059,6 +4079,19 @@ static void __mem_cgroup_free(struct mem
vfree(mem);
}
+static void mem_cgroup_free(struct mem_cgroup *mem)
+{
+ /* No more lookup */
+ mem->valid = 0;
+ rcu_assign_pointer(mem_cgroups[css_id(&mem->css)], NULL);
+ /*
+ * Because we call vfree() etc...use synchronize_rcu() rather than
+ * call_rcu();
+ */
+ synchronize_rcu();
+ __mem_cgroup_free(mem);
+}
+
static void mem_cgroup_get(struct mem_cgroup *mem)
{
atomic_inc(&mem->refcnt);
@@ -4068,7 +4101,7 @@ static void __mem_cgroup_put(struct mem_
{
if (atomic_sub_and_test(count, &mem->refcnt)) {
struct mem_cgroup *parent = parent_mem_cgroup(mem);
- __mem_cgroup_free(mem);
+ mem_cgroup_free(mem);
if (parent)
mem_cgroup_put(parent);
}
@@ -4189,9 +4222,11 @@ mem_cgroup_create(struct cgroup_subsys *
atomic_set(&mem->refcnt, 1);
mem->move_charge_at_immigrate = 0;
mutex_init(&mem->thresholds_lock);
+ atomic_inc(&mem_cgroup_num);
+ register_memcg_id(mem);
return &mem->css;
free_out:
- __mem_cgroup_free(mem);
+ mem_cgroup_free(mem);
root_mem_cgroup = NULL;
return ERR_PTR(error);
}
Index: mmotm-0811/init/Kconfig
===================================================================
--- mmotm-0811.orig/init/Kconfig
+++ mmotm-0811/init/Kconfig
@@ -594,6 +594,16 @@ config CGROUP_MEM_RES_CTLR_SWAP
Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
size is 4096bytes, 512k per 1Gbytes of swap.
+config MEM_CGROUP_MAX_GROUPS
+ int "Maximum number of memory cgroups on a system"
+ range 1 65535
+ default 8192 if 64BIT
+ default 2048 if 32BIT
+ help
+ Memory cgroup has limitation of the number of groups created.
+ Please select your favorite value. The more you allow, the more
+ memory(a pointer per group) will be consumed.
+
menuconfig CGROUP_SCHED
bool "Group CPU scheduler"
depends on EXPERIMENTAL && CGROUPS
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists