net: sock_def_readable() and friends RCU conversion

sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we
need two atomic operations (and associated dirtying) per incoming
packet.

RCU conversion is pretty much needed :

1) Add a new structure, called "struct socket_wq" to hold all fields
that will need rcu_read_lock() protection (currently: a
wait_queue_head_t and a struct fasync_struct pointer).

[Future patch will add a list anchor for wakeup coalescing]

2) Attach one of such structure to each "struct socket" created in
sock_alloc_inode().

3) Respect RCU grace period when freeing a "struct socket_wq"

4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct
socket_wq"

5) Change sk_sleep() function to use new sk->sk_wq instead of
sk->sk_sleep

6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside
a rcu_read_lock() section.

7) Change all sk_has_sleeper() callers to :
  - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock)
  - Use wq_has_sleeper() to eventually wakeup tasks.
  - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock)

8) sock_wake_async() is modified to use rcu protection as well.

9) Exceptions :
  macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq"
instead of dynamically allocated ones. They dont need rcu freeing.

Some cleanups or followups are probably needed, (possible
sk_callback_lock conversion to a spinlock for example...).

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 14 insertions, 8 deletions

diff --git a/net/atm/common.c b/net/atm/common.c
index e3e10e6..b43feb1 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -90,10 +90,13 @@ static void vcc_sock_destruct(struct sock *sk)
 
 static void vcc_def_wakeup(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
-	if (sk_has_sleeper(sk))
-		wake_up(sk_sleep(sk));
-	read_unlock(&sk->sk_callback_lock);
+	struct socket_wq *wq;
+
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (wq_has_sleeper(wq))
+		wake_up(&wq->wait);
+	rcu_read_unlock();
 }
 
 static inline int vcc_writable(struct sock *sk)
@@ -106,16 +109,19 @@ static inline int vcc_writable(struct sock *sk)
 
 static void vcc_write_space(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
+	struct socket_wq *wq;
+
+	rcu_read_lock();
 
 	if (vcc_writable(sk)) {
-		if (sk_has_sleeper(sk))
-			wake_up_interruptible(sk_sleep(sk));
+		wq = rcu_dereference(sk->sk_wq);
+		if (wq_has_sleeper(wq))
+			wake_up_interruptible(&wq->wait);
 
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
 
-	read_unlock(&sk->sk_callback_lock);
+	rcu_read_unlock();
 }
 
 static struct proto vcc_proto = {