From: KAMEZAWA Hiroyuki on
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu(a)jp.fujitsu.com>

At accounting file events per memory cgroup, we need to find memory cgroup
via page_cgroup->mem_cgroup. Now, we use lock_page_cgroup().

But, considering the context which page-cgroup for files are accessed,
we can use alternative light-weight mutual execusion in the most case.
At handling file-caches, the only race we have to take care of is "moving"
account, IOW, overwriting page_cgroup->mem_cgroup. Because file status
update is done while the page-cache is in stable state, we don't have to
take care of race with charge/uncharge.

Unlike charge/uncharge, "move" happens not so frequently. It happens only when
rmdir() and task-moving (with a special settings.)
This patch adds a race-checker for file-cache-status accounting v.s. account
moving. The new per-cpu-per-memcg counter MEM_CGROUP_ON_MOVE is added.
The routine for account move
1. Increment it before start moving
2. Call synchronize_rcu()
3. Decrement it after the end of moving.
By this, file-status-counting routine can check it needs to call
lock_page_cgroup(). In most case, I doesn't need to call it.


Changelog: 20100730
- some cleanup.
Changelog: 20100729
- replaced __this_cpu_xxx() with this_cpu_xxx
(because we don't call spinlock)
- added VM_BUG_ON().

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu(a)jp.fujitsu.com>
---
mm/memcontrol.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 66 insertions(+), 12 deletions(-)

Index: mmotm-0727/mm/memcontrol.c
===================================================================
--- mmotm-0727.orig/mm/memcontrol.c
+++ mmotm-0727/mm/memcontrol.c
@@ -88,6 +88,7 @@ enum mem_cgroup_stat_index {
MEM_CGROUP_STAT_PGPGOUT_COUNT, /* # of pages paged out */
MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
MEM_CGROUP_EVENTS, /* incremented at every pagein/pageout */
+ MEM_CGROUP_ON_MOVE, /* A check for locking move account/status */

MEM_CGROUP_STAT_NSTATS,
};
@@ -1074,7 +1075,49 @@ static unsigned int get_swappiness(struc
return swappiness;
}

-/* A routine for testing mem is not under move_account */
+static void mem_cgroup_start_move(struct mem_cgroup *mem)
+{
+ int cpu;
+ /* for fast checking in mem_cgroup_update_file_stat() etc..*/
+ spin_lock(&mc.lock);
+ for_each_possible_cpu(cpu)
+ per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
+ spin_unlock(&mc.lock);
+
+ synchronize_rcu();
+}
+
+static void mem_cgroup_end_move(struct mem_cgroup *mem)
+{
+ int cpu;
+
+ if (!mem)
+ return;
+ /* for fast checking in mem_cgroup_update_file_stat() etc..*/
+ spin_lock(&mc.lock);
+ for_each_possible_cpu(cpu)
+ per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
+ spin_unlock(&mc.lock);
+}
+
+/*
+ * mem_cgroup_is_moved -- checking a cgroup is mc.from target or not.
+ * used for avoiding race.
+ * mem_cgroup_under_move -- checking a cgroup is mc.from or mc.to or
+ * under hierarchy of them. used for waiting at
+ * memory pressure.
+ * Result of is_moved can be trusted until the end of rcu_read_unlock().
+ * The caller must do
+ * rcu_read_lock();
+ * result = mem_cgroup_is_moved();
+ * .....make use of result here....
+ * rcu_read_unlock();
+ */
+static bool mem_cgroup_is_moved(struct mem_cgroup *mem)
+{
+ VM_BUG_ON(!rcu_read_lock_held());
+ return this_cpu_read(mem->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+}

static bool mem_cgroup_under_move(struct mem_cgroup *mem)
{
@@ -1473,29 +1516,36 @@ void mem_cgroup_update_file_mapped(struc
{
struct mem_cgroup *mem;
struct page_cgroup *pc;
+ bool need_lock = false;

pc = lookup_page_cgroup(page);
if (unlikely(!pc))
return;
-
- lock_page_cgroup(pc);
+ rcu_read_lock();
mem = id_to_memcg(pc->mem_cgroup);
- if (!mem || !PageCgroupUsed(pc))
+ if (likely(mem)) {
+ if (mem_cgroup_is_moved(mem)) {
+ /* need to serialize with move_account */
+ lock_page_cgroup(pc);
+ need_lock = true;
+ mem = id_to_memcg(pc->mem_cgroup);
+ if (unlikely(!mem))
+ goto done;
+ }
+ }
+ if (unlikely(!PageCgroupUsed(pc)))
goto done;
-
- /*
- * Preemption is already disabled. We can use __this_cpu_xxx
- */
if (val > 0) {
- __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
+ this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
SetPageCgroupFileMapped(pc);
} else {
- __this_cpu_dec(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
+ this_cpu_dec(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
ClearPageCgroupFileMapped(pc);
}
-
done:
- unlock_page_cgroup(pc);
+ if (need_lock)
+ unlock_page_cgroup(pc);
+ rcu_read_unlock();
}

/*
@@ -3034,6 +3084,7 @@ move_account:
lru_add_drain_all();
drain_all_stock_sync();
ret = 0;
+ mem_cgroup_start_move(mem);
for_each_node_state(node, N_HIGH_MEMORY) {
for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
enum lru_list l;
@@ -3047,6 +3098,7 @@ move_account:
if (ret)
break;
}
+ mem_cgroup_end_move(mem);
memcg_oom_recover(mem);
/* it seems parent cgroup doesn't have enough mem */
if (ret == -ENOMEM)
@@ -4513,6 +4565,7 @@ static void mem_cgroup_clear_mc(void)
mc.to = NULL;
mc.moving_task = NULL;
spin_unlock(&mc.lock);
+ mem_cgroup_end_move(from);
memcg_oom_recover(from);
memcg_oom_recover(to);
wake_up_all(&mc.waitq);
@@ -4543,6 +4596,7 @@ static int mem_cgroup_can_attach(struct
VM_BUG_ON(mc.moved_charge);
VM_BUG_ON(mc.moved_swap);
VM_BUG_ON(mc.moving_task);
+ mem_cgroup_start_move(from);
spin_lock(&mc.lock);
mc.from = from;
mc.to = mem;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/