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>

11 files changed, 121 insertions, 68 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 = {
diff --git a/net/core/sock.c b/net/core/sock.c
index 5104175..94c4aff 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 7b3c3f3..cc196f42b 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();
 	}
 }
 
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 2d3dcb3..aadbdb5 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -195,15 +195,17 @@ EXPORT_SYMBOL_GPL(dccp_sync_mss);
 
 void dccp_write_space(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
+	struct socket_wq *wq;
 
-	if (sk_has_sleeper(sk))
-		wake_up_interruptible(sk_sleep(sk));
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (wq_has_sleeper(wq))
+		wake_up_interruptible(&wq->wait);
 	/* Should agree with poll, otherwise some programs break */
 	if (sock_writeable(sk))
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 
-	read_unlock(&sk->sk_callback_lock);
+	rcu_read_unlock();
 }
 
 /**
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 9636b7d..8be324f 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -305,11 +305,14 @@ static inline int iucv_below_msglim(struct sock *sk)
  */
 static void iucv_sock_wake_msglim(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
-	if (sk_has_sleeper(sk))
-		wake_up_interruptible_all(sk_sleep(sk));
+	struct socket_wq *wq;
+
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (wq_has_sleeper(wq))
+		wake_up_interruptible_all(&wq->wait);
 	sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
-	read_unlock(&sk->sk_callback_lock);
+	rcu_read_unlock();
 }
 
 /* Timers */
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index e2a9576..af4d38b 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -664,12 +664,12 @@ static int pep_wait_connreq(struct sock *sk, int noblock)
 		if (signal_pending(tsk))
 			return sock_intr_errno(timeo);
 
-		prepare_to_wait_exclusive(&sk->sk_socket->wait, &wait,
+		prepare_to_wait_exclusive(sk_sleep(sk), &wait,
 						TASK_INTERRUPTIBLE);
 		release_sock(sk);
 		timeo = schedule_timeout(timeo);
 		lock_sock(sk);
-		finish_wait(&sk->sk_socket->wait, &wait);
+		finish_wait(sk_sleep(sk), &wait);
 	}
 
 	return 0;
@@ -910,10 +910,10 @@ disabled:
 			goto out;
 		}
 
-		prepare_to_wait(&sk->sk_socket->wait, &wait,
+		prepare_to_wait(sk_sleep(sk), &wait,
 				TASK_INTERRUPTIBLE);
 		done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits));
-		finish_wait(&sk->sk_socket->wait, &wait);
+		finish_wait(sk_sleep(sk), &wait);
 
 		if (sk->sk_state != TCP_ESTABLISHED)
 			goto disabled;
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index c785bfd..6e9848bf 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -265,7 +265,7 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock,
 	struct pep_sock *pn = pep_sk(sk);
 	unsigned int mask = 0;
 
-	poll_wait(file, &sock->wait, wait);
+	poll_wait(file, sk_sleep(sk), wait);
 
 	switch (sk->sk_state) {
 	case TCP_LISTEN:
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index c432d76..0b9bb20 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -62,13 +62,15 @@ static inline int rxrpc_writable(struct sock *sk)
 static void rxrpc_write_space(struct sock *sk)
 {
 	_enter("%p", sk);
-	read_lock(&sk->sk_callback_lock);
+	rcu_read_lock();
 	if (rxrpc_writable(sk)) {
-		if (sk_has_sleeper(sk))
-			wake_up_interruptible(sk_sleep(sk));
+		struct socket_wq *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();
 }
 
 /*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 13d8229..d54700a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6065,7 +6065,7 @@ static void __sctp_write_space(struct sctp_association *asoc)
 			 * here by modeling from the current TCP/UDP code.
 			 * We have not tested with it yet.
 			 */
-			if (sock->fasync_list &&
+			if (sock->wq->fasync_list &&
 			    !(sk->sk_shutdown & SEND_SHUTDOWN))
 				sock_wake_async(sock,
 						SOCK_WAKE_SPACE, POLL_OUT);
diff --git a/net/socket.c b/net/socket.c
index cb7c1f6..dae8c6b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -252,9 +252,14 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 	ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
-	init_waitqueue_head(&ei->socket.wait);
+	ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL);
+	if (!ei->socket.wq) {
+		kmem_cache_free(sock_inode_cachep, ei);
+		return NULL;
+	}
+	init_waitqueue_head(&ei->socket.wq->wait);
+	ei->socket.wq->fasync_list = NULL;
 
-	ei->socket.fasync_list = NULL;
 	ei->socket.state = SS_UNCONNECTED;
 	ei->socket.flags = 0;
 	ei->socket.ops = NULL;
@@ -264,10 +269,21 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 	return &ei->vfs_inode;
 }
 
+
+static void wq_free_rcu(struct rcu_head *head)
+{
+	struct socket_wq *wq = container_of(head, struct socket_wq, rcu);
+
+	kfree(wq);
+}
+
 static void sock_destroy_inode(struct inode *inode)
 {
-	kmem_cache_free(sock_inode_cachep,
-			container_of(inode, struct socket_alloc, vfs_inode));
+	struct socket_alloc *ei;
+
+	ei = container_of(inode, struct socket_alloc, vfs_inode);
+	call_rcu(&ei->socket.wq->rcu, wq_free_rcu);
+	kmem_cache_free(sock_inode_cachep, ei);
 }
 
 static void init_once(void *foo)
@@ -513,7 +529,7 @@ void sock_release(struct socket *sock)
 		module_put(owner);
 	}
 
-	if (sock->fasync_list)
+	if (sock->wq->fasync_list)
 		printk(KERN_ERR "sock_release: fasync list not empty!\n");
 
 	percpu_sub(sockets_in_use, 1);
@@ -1080,9 +1096,9 @@ static int sock_fasync(int fd, struct file *filp, int on)
 
 	lock_sock(sk);
 
-	fasync_helper(fd, filp, on, &sock->fasync_list);
+	fasync_helper(fd, filp, on, &sock->wq->fasync_list);
 
-	if (!sock->fasync_list)
+	if (!sock->wq->fasync_list)
 		sock_reset_flag(sk, SOCK_FASYNC);
 	else
 		sock_set_flag(sk, SOCK_FASYNC);
@@ -1091,12 +1107,20 @@ static int sock_fasync(int fd, struct file *filp, int on)
 	return 0;
 }
 
-/* This function may be called only under socket lock or callback_lock */
+/* This function may be called only under socket lock or callback_lock or rcu_lock */
 
 int sock_wake_async(struct socket *sock, int how, int band)
 {
-	if (!sock || !sock->fasync_list)
+	struct socket_wq *wq;
+
+	if (!sock)
 		return -1;
+	rcu_read_lock();
+	wq = rcu_dereference(sock->wq);
+	if (!wq || !wq->fasync_list) {
+		rcu_read_unlock();
+		return -1;
+	}
 	switch (how) {
 	case SOCK_WAKE_WAITD:
 		if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
@@ -1108,11 +1132,12 @@ int sock_wake_async(struct socket *sock, int how, int band)
 		/* fall through */
 	case SOCK_WAKE_IO:
 call_kill:
-		kill_fasync(&sock->fasync_list, SIGIO, band);
+		kill_fasync(&wq->fasync_list, SIGIO, band);
 		break;
 	case SOCK_WAKE_URG:
-		kill_fasync(&sock->fasync_list, SIGURG, band);
+		kill_fasync(&wq->fasync_list, SIGURG, band);
 	}
+	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 87c0360..fef2cc5 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -313,13 +313,16 @@ static inline int unix_writable(struct sock *sk)
 
 static void unix_write_space(struct sock *sk)
 {
-	read_lock(&sk->sk_callback_lock);
+	struct socket_wq *wq;
+
+	rcu_read_lock();
 	if (unix_writable(sk)) {
-		if (sk_has_sleeper(sk))
-			wake_up_interruptible_sync(sk_sleep(sk));
+		wq = rcu_dereference(sk->sk_wq);
+		if (wq_has_sleeper(wq))
+			wake_up_interruptible_sync(&wq->wait);
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
-	read_unlock(&sk->sk_callback_lock);
+	rcu_read_unlock();
 }
 
 /* When dgram socket disconnects (or changes its peer), we clear its receive
@@ -406,9 +409,7 @@ static int unix_release_sock(struct sock *sk, int embrion)
 				skpair->sk_err = ECONNRESET;
 			unix_state_unlock(skpair);
 			skpair->sk_state_change(skpair);
-			read_lock(&skpair->sk_callback_lock);
 			sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
-			read_unlock(&skpair->sk_callback_lock);
 		}
 		sock_put(skpair); /* It may now die */
 		unix_peer(sk) = NULL;
@@ -1142,7 +1143,7 @@ restart:
 	newsk->sk_peercred.pid	= task_tgid_vnr(current);
 	current_euid_egid(&newsk->sk_peercred.uid, &newsk->sk_peercred.gid);
 	newu = unix_sk(newsk);
-	newsk->sk_sleep		= &newu->peer_wait;
+	newsk->sk_wq		= &newu->peer_wq;
 	otheru = unix_sk(other);
 
 	/* copy address information from listening to new sock*/
@@ -1931,12 +1932,10 @@ static int unix_shutdown(struct socket *sock, int mode)
 			other->sk_shutdown |= peer_mode;
 			unix_state_unlock(other);
 			other->sk_state_change(other);
-			read_lock(&other->sk_callback_lock);
 			if (peer_mode == SHUTDOWN_MASK)
 				sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
 			else if (peer_mode & RCV_SHUTDOWN)
 				sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
-			read_unlock(&other->sk_callback_lock);
 		}
 		if (other)
 			sock_put(other);