rxrpc: Don't hold a ref for connection workqueue

Currently, rxrpc gives the connection's work item a ref on the connection
when it queues it - and this is called from the timer expiration function.
The problem comes when queue_work() fails (ie. the work item is already
queued): the timer routine must put the ref - but this may cause the
cleanup code to run.

This has the unfortunate effect that the cleanup code may then be run in
softirq context - which means that any spinlocks it might need to touch
have to be guarded to disable softirqs (ie. they need a "_bh" suffix).

 (1) Don't give a ref to the work item.

 (2) Simplify handling of service connections by adding a separate active
     count so that the refcount isn't also used for this.

 (3) Connection destruction for both client and service connections can
     then be cleaned up by putting rxrpc_put_connection() out of line and
     making a tidy progression through the destruction code (offloaded to a
     workqueue if put from softirq or processor function context).  The RCU
     part of the cleanup then only deals with the freeing at the end.

 (4) Make rxrpc_queue_conn() return immediately if it sees the active count
     is -1 rather then queuing the connection.

 (5) Make sure that the cleanup routine waits for the work item to
     complete.

 (6) Stash the rxrpc_net pointer in the conn struct so that the rcu free
     routine can use it, even if the local endpoint has been freed.

Unfortunately, neither the timer nor the work item can simply get around
the problem by just using refcount_inc_not_zero() as the waits would still
have to be done, and there would still be the possibility of having to put
the ref in the expiration function.

Note the connection work item is mostly going to go away with the main
event work being transferred to the I/O thread, so the wait in (6) will
become obsolete.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org

1 files changed, 8 insertions, 23 deletions

diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 34ff6fa85c32..9485a3d18f29 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -51,7 +51,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
 static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn,
 					  gfp_t gfp)
 {
-	struct rxrpc_net *rxnet = conn->local->rxnet;
+	struct rxrpc_net *rxnet = conn->rxnet;
 	int id;
 
 	_enter("");
@@ -179,7 +179,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp)
 
 	_enter("");
 
-	conn = rxrpc_alloc_connection(gfp);
+	conn = rxrpc_alloc_connection(rxnet, gfp);
 	if (!conn) {
 		_leave(" = -ENOMEM");
 		return ERR_PTR(-ENOMEM);
@@ -243,7 +243,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
 	if (!conn)
 		goto dont_reuse;
 
-	rxnet = conn->local->rxnet;
+	rxnet = conn->rxnet;
 	if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags))
 		goto dont_reuse;
 
@@ -970,7 +970,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
 /*
  * Clean up a dead client connection.
  */
-static void rxrpc_kill_client_conn(struct rxrpc_connection *conn)
+void rxrpc_kill_client_conn(struct rxrpc_connection *conn)
 {
 	struct rxrpc_local *local = conn->local;
 	struct rxrpc_net *rxnet = local->rxnet;
@@ -981,23 +981,6 @@ static void rxrpc_kill_client_conn(struct rxrpc_connection *conn)
 	atomic_dec(&rxnet->nr_client_conns);
 
 	rxrpc_put_client_connection_id(conn);
-	rxrpc_kill_connection(conn);
-}
-
-/*
- * Clean up a dead client connections.
- */
-void rxrpc_put_client_conn(struct rxrpc_connection *conn,
-			   enum rxrpc_conn_trace why)
-{
-	unsigned int debug_id = conn->debug_id;
-	bool dead;
-	int r;
-
-	dead = __refcount_dec_and_test(&conn->ref, &r);
-	trace_rxrpc_conn(debug_id, r - 1, why);
-	if (dead)
-		rxrpc_kill_client_conn(conn);
 }
 
 /*
@@ -1023,7 +1006,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work)
 	}
 
 	/* Don't double up on the discarding */
-	if (!spin_trylock(&rxnet->client_conn_discard_lock)) {
+	if (!mutex_trylock(&rxnet->client_conn_discard_lock)) {
 		_leave(" [already]");
 		return;
 	}
@@ -1061,6 +1044,7 @@ next:
 			goto not_yet_expired;
 	}
 
+	atomic_dec(&conn->active);
 	trace_rxrpc_client(conn, -1, rxrpc_client_discard);
 	list_del_init(&conn->cache_link);
 
@@ -1087,7 +1071,7 @@ not_yet_expired:
 
 out:
 	spin_unlock(&rxnet->client_conn_cache_lock);
-	spin_unlock(&rxnet->client_conn_discard_lock);
+	mutex_unlock(&rxnet->client_conn_discard_lock);
 	_leave("");
 }
 
@@ -1127,6 +1111,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
 	list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns,
 				 cache_link) {
 		if (conn->local == local) {
+			atomic_dec(&conn->active);
 			trace_rxrpc_client(conn, -1, rxrpc_client_discard);
 			list_move(&conn->cache_link, &graveyard);
 		}