[PATCH 1/2] mem_cgroup: optimize the atomic count of wb_completion

[brookxu]

From: Chunguang Xu <brookxu@xxxxxxxxxxx>

In order to track inflight foreign writeback, we init
wb_completion.cnt to 1. For normal writeback, this cause
wb_wait_for_completion() to perform meaningless atomic
operations. Since foreign writebacks rarely occur in most
scenarios, we can init wb_completion.cnt to 0 and set
frn.done.cnt to 1. In this way we can avoid unnecessary
atomic operations.

Signed-off-by: Chunguang Xu <brookxu@xxxxxxxxxxx>
---
 fs/fs-writeback.c                | 1 -
 include/linux/backing-dev-defs.h | 2 +-
 mm/memcontrol.c                  | 7 ++++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 81ec192..1ef10f2 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -186,7 +186,6 @@ static void wb_queue_work(struct bdi_writeback *wb,
  */
 void wb_wait_for_completion(struct wb_completion *done)
 {
-	atomic_dec(&done->cnt);		/* put down the initial count */
 	wait_event(*done->waitq, !atomic_read(&done->cnt));
 }
 
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 3320700..38bd571 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -71,7 +71,7 @@ struct wb_completion {
 };
 
 #define __WB_COMPLETION_INIT(_waitq)	\
-	(struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) }
+	(struct wb_completion){ .cnt = ATOMIC_INIT(0), .waitq = (_waitq) }
 
 /*
  * If one wants to wait for one or more wb_writeback_works, each work's
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b762215..3e1384a6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5168,9 +5168,10 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 #endif
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
-	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
-		memcg->cgwb_frn[i].done =
-			__WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
+	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
+		atomic_set(&memcg->cgwb_frn[i].done.cnt, 1);
+		memcg->cgwb_frn[i].done.waitq = &memcg_cgwb_frn_waitq;
+	}
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	spin_lock_init(&memcg->deferred_split_queue.split_queue_lock);
-- 
1.8.3.1