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, 21 insertions, 13 deletions

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index d97e1fd234ba..1c4110df343e 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -37,6 +37,7 @@
 struct macvtap_queue {
 	struct sock sk;
 	struct socket sock;
+	struct socket_wq wq;
 	struct macvlan_dev *vlan;
 	struct file *file;
 	unsigned int flags;
@@ -242,12 +243,15 @@ static struct rtnl_link_ops macvtap_link_ops __read_mostly = {
 
 static void macvtap_sock_write_space(struct sock *sk)
 {
+	wait_queue_head_t *wqueue;
+
 	if (!sock_writeable(sk) ||
 	    !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
 		return;
 
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-		wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND);
+	wqueue = sk_sleep(sk);
+	if (wqueue && waitqueue_active(wqueue))
+		wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND);
 }
 
 static int macvtap_open(struct inode *inode, struct file *file)
@@ -272,7 +276,8 @@ static int macvtap_open(struct inode *inode, struct file *file)
 	if (!q)
 		goto out;
 
-	init_waitqueue_head(&q->sock.wait);
+	q->sock.wq = &q->wq;
+	init_waitqueue_head(&q->wq.wait);
 	q->sock.type = SOCK_RAW;
 	q->sock.state = SS_CONNECTED;
 	q->sock.file = file;
@@ -308,7 +313,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait)
 		goto out;
 
 	mask = 0;
-	poll_wait(file, &q->sock.wait, wait);
+	poll_wait(file, &q->wq.wait, wait);
 
 	if (!skb_queue_empty(&q->sk.sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 20a17938c62b..e525a6cf5587 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -109,7 +109,7 @@ struct tun_struct {
 
 	struct tap_filter       txflt;
 	struct socket		socket;
-
+	struct socket_wq	wq;
 #ifdef TUN_DEBUG
 	int debug;
 #endif
@@ -323,7 +323,7 @@ static void tun_net_uninit(struct net_device *dev)
 	/* Inform the methods they need to stop using the dev.
 	 */
 	if (tfile) {
-		wake_up_all(&tun->socket.wait);
+		wake_up_all(&tun->wq.wait);
 		if (atomic_dec_and_test(&tfile->count))
 			__tun_detach(tun);
 	}
@@ -398,7 +398,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Notify and wake up reader process */
 	if (tun->flags & TUN_FASYNC)
 		kill_fasync(&tun->fasync, SIGIO, POLL_IN);
-	wake_up_interruptible_poll(&tun->socket.wait, POLLIN |
+	wake_up_interruptible_poll(&tun->wq.wait, POLLIN |
 				   POLLRDNORM | POLLRDBAND);
 	return NETDEV_TX_OK;
 
@@ -498,7 +498,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
 
 	DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name);
 
-	poll_wait(file, &tun->socket.wait, wait);
+	poll_wait(file, &tun->wq.wait, wait);
 
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
@@ -773,7 +773,7 @@ static ssize_t tun_do_read(struct tun_struct *tun,
 
 	DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name);
 
-	add_wait_queue(&tun->socket.wait, &wait);
+	add_wait_queue(&tun->wq.wait, &wait);
 	while (len) {
 		current->state = TASK_INTERRUPTIBLE;
 
@@ -804,7 +804,7 @@ static ssize_t tun_do_read(struct tun_struct *tun,
 	}
 
 	current->state = TASK_RUNNING;
-	remove_wait_queue(&tun->socket.wait, &wait);
+	remove_wait_queue(&tun->wq.wait, &wait);
 
 	return ret;
 }
@@ -861,6 +861,7 @@ static struct rtnl_link_ops tun_link_ops __read_mostly = {
 static void tun_sock_write_space(struct sock *sk)
 {
 	struct tun_struct *tun;
+	wait_queue_head_t *wqueue;
 
 	if (!sock_writeable(sk))
 		return;
@@ -868,8 +869,9 @@ static void tun_sock_write_space(struct sock *sk)
 	if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
 		return;
 
-	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
-		wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT |
+	wqueue = sk_sleep(sk);
+	if (wqueue && waitqueue_active(wqueue))
+		wake_up_interruptible_sync_poll(wqueue, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
 
 	tun = tun_sk(sk)->tun;
@@ -1039,7 +1041,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		if (!sk)
 			goto err_free_dev;
 
-		init_waitqueue_head(&tun->socket.wait);
+		tun->socket.wq = &tun->wq;
+		init_waitqueue_head(&tun->wq.wait);
 		tun->socket.ops = &tun_socket_ops;
 		sock_init_data(&tun->socket, sk);
 		sk->sk_write_space = tun_sock_write_space;