| 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: <20100924181550.d1757901.kamezawa.hiroyu@jp.fujitsu.com>
Date: Fri, 24 Sep 2010 18:15:50 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc: "linux-mm@...ck.org" <linux-mm@...ck.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"balbir@...ux.vnet.ibm.com" <balbir@...ux.vnet.ibm.com>,
"nishimura@....nes.nec.co.jp" <nishimura@....nes.nec.co.jp>,
"akpm@...ux-foundation.org" <akpm@...ux-foundation.org>
Subject: [RFC][PATCH 1/2] memcg: special ID lookup routine
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
It seems previous patches are not welcomed, this is a revised one.
My purpose is to replace pc->mem_cgroup to be pc->mem_cgroup_id and to prevent
using more memory when pc->blkio_cgroup_id is added.
As 1st step, this patch implements a lookup table from ID.
For usual lookup, css_lookup() will work enough well but it may have to
access several level of idr radix-tree. Memory cgroup's limit is 65536 and
as far as I here, there are a user who uses 2000+ memory cgroup on a system.
And with generic rcu based lookup routine, the caller has to
Type A:
rcu_read_lock()
obj = obj_lookup()
atomic_inc(obj->refcnt)
rcu_read_unlock()
/* do jobs */
Type B:
rcu_read_lock()
obj = rcu_lookup()
/* do jobs */
rcu_read_unlock()
Under some spinlock in many case.
(Type A is very bad in busy routine and even type B has to check the
object is alive or not. It's not no cost)
This is complicated.
Because page_cgroup -> mem_cgroup information is required at every LRU
operatons, I think it's worth to add a special lookup routine for reducing
cache footprint and, with some limitaton, lookup routine can be RCU free.
Note:
- memcg_lookup() is defined but not used. it's called in other patch.
Changelog:
- no hooks to cgroup.
- no limitation of the number of memcg.
- delay table allocation until memory cgroup is really used.
- No RCU routine. (depends on the limitation to callers newly added.)
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
---
mm/memcontrol.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 67 insertions(+)
Index: mmotm-0922/mm/memcontrol.c
===================================================================
--- mmotm-0922.orig/mm/memcontrol.c
+++ mmotm-0922/mm/memcontrol.c
@@ -198,6 +198,7 @@ static void mem_cgroup_oom_notify(struct
*/
struct mem_cgroup {
struct cgroup_subsys_state css;
+ bool cached;
/*
* the counter to account for memory usage
*/
@@ -352,6 +353,65 @@ static void mem_cgroup_put(struct mem_cg
static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
static void drain_all_stock_async(void);
+#define MEMCG_ARRAY_SIZE (sizeof(struct mem_cgroup *) *(65536))
+struct mem_cgroup **memcg_array __read_mostly;
+DEFINE_SPINLOCK(memcg_array_lock);
+
+/*
+ * A quick lookup routine for memory cgroup via ID. This can be used
+ * until destroy() is called against memory cgroup. Then, in most case,
+ * there must be page_cgroups or tasks which points to memcg.
+ * So, cannot be used for swap_cgroup reference.
+ */
+static struct mem_cgroup *memcg_lookup(int id)
+{
+ if (id == 0)
+ return NULL;
+ if (id == 1)
+ return root_mem_cgroup;
+ return *(memcg_array + id);
+}
+
+static void memcg_lookup_set(struct mem_cgroup *mem)
+{
+ int id;
+
+ if (likely(mem->cached) || mem == root_mem_cgroup)
+ return;
+ id = css_id(&mem->css);
+ /* There are race with other "set" entry. need to avoid double refcnt */
+ spin_lock(&memcg_array_lock);
+ if (!(*(memcg_array + id))) {
+ mem_cgroup_get(mem);
+ *(memcg_array + id) = mem;
+ mem->cached = true;
+ }
+ spin_unlock(&memcg_array_lock);
+}
+
+static void memcg_lookup_clear(struct mem_cgroup *mem)
+{
+ int id = css_id(&mem->css);
+ /* No race with other look up/set/unset entry */
+ *(memcg_array + id) = NULL;
+ mem_cgroup_put(mem);
+}
+
+static int init_mem_cgroup_lookup_array(void)
+{
+ int size;
+
+ if (memcg_array)
+ return 0;
+
+ size = MEMCG_ARRAY_SIZE;
+ memcg_array = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+ PAGE_KERNEL);
+ if (!memcg_array)
+ return -ENOMEM;
+
+ return 0;
+}
static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
@@ -2096,6 +2156,7 @@ static void __mem_cgroup_commit_charge(s
mem_cgroup_cancel_charge(mem);
return;
}
+ memcg_lookup_set(mem);
pc->mem_cgroup = mem;
/*
@@ -4341,6 +4402,10 @@ mem_cgroup_create(struct cgroup_subsys *
}
hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
} else {
+ /* Allocation of lookup array is delayd until creat cgroup */
+ error = init_mem_cgroup_lookup_array();
+ if (error == -ENOMEM)
+ goto free_out;
parent = mem_cgroup_from_cont(cont->parent);
mem->use_hierarchy = parent->use_hierarchy;
mem->oom_kill_disable = parent->oom_kill_disable;
@@ -4389,6 +4454,8 @@ static void mem_cgroup_destroy(struct cg
{
struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+ memcg_lookup_clear(mem);
+
mem_cgroup_put(mem);
}
--
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