fasync: RCU and fine grained locking

kill_fasync() uses a central rwlock, candidate for RCU conversion, to
avoid cache line ping pongs on SMP.

fasync_remove_entry() and fasync_add_entry() can disable IRQS on a short
section instead during whole list scan.

Use a spinlock per fasync_struct to synchronize kill_fasync_rcu() and
fasync_{remove|add}_entry(). This spinlock is IRQ safe, so sock_fasync()
doesnt need its own implementation and can use fasync_helper(), to
reduce code size and complexity.

We can remove __kill_fasync() direct use in net/socket.c, and rename it
to kill_fasync_rcu().

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 39d57bc..018d382f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1280,10 +1280,12 @@
 
 
 struct fasync_struct {
-	int	magic;
-	int	fa_fd;
-	struct	fasync_struct	*fa_next; /* singly linked list */
-	struct	file 		*fa_file;
+	spinlock_t		fa_lock;
+	int			magic;
+	int			fa_fd;
+	struct fasync_struct	*fa_next; /* singly linked list */
+	struct file		*fa_file;
+	struct rcu_head		fa_rcu;
 };
 
 #define FASYNC_MAGIC 0x4601
@@ -1292,8 +1294,6 @@
 extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
 /* can be called from interrupts */
 extern void kill_fasync(struct fasync_struct **, int, int);
-/* only for net: no internal synchronization */
-extern void __kill_fasync(struct fasync_struct *, int, int);
 
 extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
 extern int f_setown(struct file *filp, unsigned long arg, int force);