rxrpc: Calls shouldn't hold socket refs

rxrpc calls shouldn't hold refs on the sock struct.  This was done so that
the socket wouldn't go away whilst the call was in progress, such that the
call could reach the socket's queues.

However, we can mark the socket as requiring an RCU release and rely on the
RCU read lock.

To make this work, we do:

 (1) rxrpc_release_call() removes the call's call user ID.  This is now
     only called from socket operations and not from the call processor:

	rxrpc_accept_call() / rxrpc_kernel_accept_call()
	rxrpc_reject_call() / rxrpc_kernel_reject_call()
	rxrpc_kernel_end_call()
	rxrpc_release_calls_on_socket()
	rxrpc_recvmsg()

     Though it is also called in the cleanup path of
     rxrpc_accept_incoming_call() before we assign a user ID.

 (2) Pass the socket pointer into rxrpc_release_call() rather than getting
     it from the call so that we can get rid of uninitialised calls.

 (3) Fix call processor queueing to pass a ref to the work queue and to
     release that ref at the end of the processor function (or to pass it
     back to the work queue if we have to requeue).

 (4) Skip out of the call processor function asap if the call is complete
     and don't requeue it if the call is complete.

 (5) Clean up the call immediately that the refcount reaches 0 rather than
     trying to defer it.  Actual deallocation is deferred to RCU, however.

 (6) Don't hold socket refs for allocated calls.

 (7) Use the RCU read lock when queueing a message on a socket and treat
     the call's socket pointer according to RCU rules and check it for
     NULL.

     We also need to use the RCU read lock when viewing a call through
     procfs.

 (8) Transmit the final ACK/ABORT to a client call in rxrpc_release_call()
     if this hasn't been done yet so that we can then disconnect the call.
     Once the call is disconnected, it won't have any access to the
     connection struct and the UDP socket for the call work processor to be
     able to send the ACK.  Terminal retransmission will be handled by the
     connection processor.

 (9) Release all calls immediately on the closing of a socket rather than
     trying to defer this.  Incomplete calls will be aborted.

The call refcount model is much simplified.  Refs are held on the call by:

 (1) A socket's user ID tree.

 (2) A socket's incoming call secureq and acceptq.

 (3) A kernel service that has a call in progress.

 (4) A queued call work processor.  We have to take care to put any call
     that we failed to queue.

 (5) sk_buffs on a socket's receive queue.  A future patch will get rid of
     this.

Whilst we're at it, we can do:

 (1) Get rid of the RXRPC_CALL_EV_RELEASE event.  Release is now done
     entirely from the socket routines and never from the call's processor.

 (2) Get rid of the RXRPC_CALL_DEAD state.  Calls now end in the
     RXRPC_CALL_COMPLETE state.

 (3) Get rid of the rxrpc_call::destroyer work item.  Calls are now torn
     down when their refcount reaches 0 and then handed over to RCU for
     final cleanup.

 (4) Get rid of the rxrpc_call::deadspan timer.  Calls are cleaned up
     immediately they're finished with and don't hang around.
     Post-completion retransmission is handled by the connection processor
     once the call is disconnected.

 (5) Get rid of the dead call expiry setting as there's no longer a timer
     to set.

 (6) rxrpc_destroy_all_calls() can just check that the call list is empty.

Signed-off-by: David Howells <dhowells@redhat.com>

1 files changed, 14 insertions, 12 deletions

diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 8267f42a7753..79f3f585cdc3 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -39,7 +39,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
 			bool force, bool terminal)
 {
 	struct rxrpc_skb_priv *sp;
-	struct rxrpc_sock *rx = call->socket;
+	struct rxrpc_sock *rx;
 	struct sock *sk;
 	int ret;
 
@@ -59,7 +59,15 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
 		return 0;
 	}
 
+	/* The socket may go away under us */
+	ret = 0;
+	rcu_read_lock();
+	rx = rcu_dereference(call->socket);
+	if (!rx)
+		goto out;
 	sk = &rx->sk;
+	if (sock_flag(sk, SOCK_DEAD))
+		goto out;
 
 	if (!force) {
 		/* cast skb->rcvbuf to unsigned...  It's pointless, but
@@ -78,7 +86,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
 	spin_lock_bh(&sk->sk_receive_queue.lock);
 	if (!test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags) &&
 	    !test_bit(RXRPC_CALL_RELEASED, &call->flags) &&
-	    call->socket->sk.sk_state != RXRPC_CLOSE) {
+	    sk->sk_state != RXRPC_CLOSE) {
 		skb->destructor = rxrpc_packet_destructor;
 		skb->dev = NULL;
 		skb->sk = sk;
@@ -104,8 +112,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
 			__skb_queue_tail(&sk->sk_receive_queue, skb);
 			spin_unlock_bh(&sk->sk_receive_queue.lock);
 
-			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk);
+			sk->sk_data_ready(sk);
 		}
 		skb = NULL;
 	} else {
@@ -115,6 +122,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
 
 out:
 	rxrpc_free_skb(skb);
+	rcu_read_unlock();
 
 	_leave(" = %d", ret);
 	return ret;
@@ -266,7 +274,7 @@ enqueue_packet:
 	skb_queue_tail(&call->rx_queue, skb);
 	atomic_inc(&call->ackr_not_idle);
 	read_lock(&call->state_lock);
-	if (call->state < RXRPC_CALL_DEAD)
+	if (call->state < RXRPC_CALL_COMPLETE)
 		rxrpc_queue_call(call);
 	read_unlock(&call->state_lock);
 	_leave(" = 0 [queued]");
@@ -408,7 +416,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb)
 	case RXRPC_PACKET_TYPE_ACK:
 		/* ACK processing is done in process context */
 		read_lock_bh(&call->state_lock);
-		if (call->state < RXRPC_CALL_DEAD) {
+		if (call->state < RXRPC_CALL_COMPLETE) {
 			skb_queue_tail(&call->rx_queue, skb);
 			rxrpc_queue_call(call);
 			skb = NULL;
@@ -511,9 +519,6 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn,
 
 	read_lock(&call->state_lock);
 	switch (call->state) {
-	case RXRPC_CALL_DEAD:
-		goto dead_call;
-
 	case RXRPC_CALL_COMPLETE:
 		switch (call->completion) {
 		case RXRPC_CALL_LOCALLY_ABORTED:
@@ -538,7 +543,6 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn,
 	}
 
 	read_unlock(&call->state_lock);
-	rxrpc_get_call(call, rxrpc_call_got);
 
 	if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
 	    sp->hdr.flags & RXRPC_JUMBO_PACKET)
@@ -546,12 +550,10 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn,
 	else
 		rxrpc_fast_process_packet(call, skb);
 
-	rxrpc_put_call(call, rxrpc_call_put);
 	goto done;
 
 resend_final_ack:
 	_debug("final ack again");
-	rxrpc_get_call(call, rxrpc_call_got);
 	set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events);
 	rxrpc_queue_call(call);
 	goto free_unlock;