Revert "f2fs: use percpu_rw_semaphore"

LKP reported -36.3% regression of fsmark.files_per_sec due to this patch.
I've confirmed that fxmark [1] has also slight regression for DWAL.

[1] https://github.com/sslab-gatech/fxmark

This reverts commit ec795418c41850056feb956534edf059dc1155d4.
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 675fa79..14f5fe2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -538,7 +538,7 @@
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
 	struct radix_tree_root nat_set_root;/* root of the nat set cache */
-	struct percpu_rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
+	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	unsigned int nat_cnt;		/* the # of cached nat entries */
 	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
@@ -787,7 +787,7 @@
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
 	struct inode *meta_inode;		/* cache meta blocks */
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
-	struct percpu_rw_semaphore cp_rwsem;		/* blocking FS operations */
+	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
 	wait_queue_head_t cp_wait;
 	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
@@ -1074,22 +1074,22 @@
 
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 {
-	percpu_down_read(&sbi->cp_rwsem);
+	down_read(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 {
-	percpu_up_read(&sbi->cp_rwsem);
+	up_read(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	percpu_down_write(&sbi->cp_rwsem);
+	down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
 {
-	percpu_up_write(&sbi->cp_rwsem);
+	up_write(&sbi->cp_rwsem);
 }
 
 static inline int __get_cp_reason(struct f2fs_sb_info *sbi)