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>

2 files changed, 38 insertions, 22 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 51041759517e..94c4affdda9b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1211,7 +1211,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
-		newsk->sk_sleep	 = NULL;
+		newsk->sk_wq = NULL;
 
 		if (newsk->sk_prot->sockets_allocated)
 			percpu_counter_inc(newsk->sk_prot->sockets_allocated);
@@ -1800,41 +1800,53 @@ EXPORT_SYMBOL(sock_no_sendpage);
 
 static void sock_def_wakeup(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
-	if (sk_has_sleeper(sk))
-		wake_up_interruptible_all(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_interruptible_all(&wq->wait);
+	rcu_read_unlock();
 }
 
 static void sock_def_error_report(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
-	if (sk_has_sleeper(sk))
-		wake_up_interruptible_poll(sk_sleep(sk), POLLERR);
+	struct socket_wq *wq;
+
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (wq_has_sleeper(wq))
+		wake_up_interruptible_poll(&wq->wait, POLLERR);
 	sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
-	read_unlock(&sk->sk_callback_lock);
+	rcu_read_unlock();
 }
 
 static void sock_def_readable(struct sock *sk, int len)
 {
-	read_lock(&sk->sk_callback_lock);
-	if (sk_has_sleeper(sk))
-		wake_up_interruptible_sync_poll(sk_sleep(sk), POLLIN |
+	struct socket_wq *wq;
+
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (wq_has_sleeper(wq))
+		wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
 						POLLRDNORM | POLLRDBAND);
 	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
-	read_unlock(&sk->sk_callback_lock);
+	rcu_read_unlock();
 }
 
 static void sock_def_write_space(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
+	struct socket_wq *wq;
+
+	rcu_read_lock();
 
 	/* Do not wake up a writer until he can make "significant"
 	 * progress.  --DaveM
 	 */
 	if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
-		if (sk_has_sleeper(sk))
-			wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT |
+		wq = rcu_dereference(sk->sk_wq);
+		if (wq_has_sleeper(wq))
+			wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
 
 		/* Should agree with poll, otherwise some programs break */
@@ -1842,7 +1854,7 @@ static void sock_def_write_space(struct sock *sk)
 			sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
 
-	read_unlock(&sk->sk_callback_lock);
+	rcu_read_unlock();
 }
 
 static void sock_def_destruct(struct sock *sk)
@@ -1896,10 +1908,10 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 
 	if (sock) {
 		sk->sk_type	=	sock->type;
-		sk->sk_sleep	=	&sock->wait;
+		sk->sk_wq	=	sock->wq;
 		sock->sk	=	sk;
 	} else
-		sk->sk_sleep	=	NULL;
+		sk->sk_wq	=	NULL;
 
 	spin_lock_init(&sk->sk_dst_lock);
 	rwlock_init(&sk->sk_callback_lock);
diff --git a/net/core/stream.c b/net/core/stream.c
index 7b3c3f30b107..cc196f42b8d8 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -28,15 +28,19 @@
 void sk_stream_write_space(struct sock *sk)
 {
 	struct socket *sock = sk->sk_socket;
+	struct socket_wq *wq;
 
 	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) {
 		clear_bit(SOCK_NOSPACE, &sock->flags);
 
-		if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-			wake_up_interruptible_poll(sk_sleep(sk), POLLOUT |
+		rcu_read_lock();
+		wq = rcu_dereference(sk->sk_wq);
+		if (wq_has_sleeper(wq))
+			wake_up_interruptible_poll(&wq->wait, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
-		if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
+		if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
 			sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT);
+		rcu_read_unlock();
 	}
 }