rxrpc: Support network namespacing

Support network namespacing in AF_RXRPC with the following changes:

 (1) All the local endpoint, peer and call lists, locks, counters, etc. are
     moved into the per-namespace record.

 (2) All the connection tracking is moved into the per-namespace record
     with the exception of the client connection ID tree, which is kept
     global so that connection IDs are kept unique per-machine.

 (3) Each namespace gets its own epoch.  This allows each network namespace
     to pretend to be a separate client machine.

 (4) The /proc/net/rxrpc_xxx files are now called /proc/net/rxrpc/xxx and
     the contents reflect the namespace.

fs/afs/ should be okay with this patch as it explicitly requires the current
net namespace to be init_net to permit a mount to proceed at the moment.  It
will, however, need updating so that cells, IP addresses and DNS records are
per-namespace also.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 25 insertions, 30 deletions

diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index b0ecb770fdce..ade4d3d0b2a7 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -22,13 +22,6 @@
  */
 unsigned int rxrpc_connection_expiry = 10 * 60;
 
-static void rxrpc_connection_reaper(struct work_struct *work);
-
-LIST_HEAD(rxrpc_connections);
-LIST_HEAD(rxrpc_connection_proc_list);
-DEFINE_RWLOCK(rxrpc_connection_lock);
-static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper);
-
 static void rxrpc_destroy_connection(struct rcu_head *);
 
 /*
@@ -222,15 +215,17 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
  */
 void rxrpc_kill_connection(struct rxrpc_connection *conn)
 {
+	struct rxrpc_net *rxnet = conn->params.local->rxnet;
+
 	ASSERT(!rcu_access_pointer(conn->channels[0].call) &&
 	       !rcu_access_pointer(conn->channels[1].call) &&
 	       !rcu_access_pointer(conn->channels[2].call) &&
 	       !rcu_access_pointer(conn->channels[3].call));
 	ASSERT(list_empty(&conn->cache_link));
 
-	write_lock(&rxrpc_connection_lock);
+	write_lock(&rxnet->conn_lock);
 	list_del_init(&conn->proc_link);
-	write_unlock(&rxrpc_connection_lock);
+	write_unlock(&rxnet->conn_lock);
 
 	/* Drain the Rx queue.  Note that even though we've unpublished, an
 	 * incoming packet could still be being added to our Rx queue, so we
@@ -309,14 +304,17 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
  */
 void rxrpc_put_service_conn(struct rxrpc_connection *conn)
 {
+	struct rxrpc_net *rxnet;
 	const void *here = __builtin_return_address(0);
 	int n;
 
 	n = atomic_dec_return(&conn->usage);
 	trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here);
 	ASSERTCMP(n, >=, 0);
-	if (n == 0)
-		rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
+	if (n == 0) {
+		rxnet = conn->params.local->rxnet;
+		rxrpc_queue_delayed_work(&rxnet->service_conn_reaper, 0);
+	}
 }
 
 /*
@@ -348,9 +346,12 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu)
 /*
  * reap dead service connections
  */
-static void rxrpc_connection_reaper(struct work_struct *work)
+void rxrpc_service_connection_reaper(struct work_struct *work)
 {
 	struct rxrpc_connection *conn, *_p;
+	struct rxrpc_net *rxnet =
+		container_of(to_delayed_work(work),
+			     struct rxrpc_net, service_conn_reaper);
 	unsigned long reap_older_than, earliest, idle_timestamp, now;
 
 	LIST_HEAD(graveyard);
@@ -361,8 +362,8 @@ static void rxrpc_connection_reaper(struct work_struct *work)
 	reap_older_than = now - rxrpc_connection_expiry * HZ;
 	earliest = ULONG_MAX;
 
-	write_lock(&rxrpc_connection_lock);
-	list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) {
+	write_lock(&rxnet->conn_lock);
+	list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) {
 		ASSERTCMP(atomic_read(&conn->usage), >, 0);
 		if (likely(atomic_read(&conn->usage) > 1))
 			continue;
@@ -393,12 +394,12 @@ static void rxrpc_connection_reaper(struct work_struct *work)
 
 		list_move_tail(&conn->link, &graveyard);
 	}
-	write_unlock(&rxrpc_connection_lock);
+	write_unlock(&rxnet->conn_lock);
 
 	if (earliest != ULONG_MAX) {
 		_debug("reschedule reaper %ld", (long) earliest - now);
 		ASSERT(time_after(earliest, now));
-		rxrpc_queue_delayed_work(&rxrpc_connection_reap,
+		rxrpc_queue_delayed_work(&rxnet->client_conn_reaper,
 					 earliest - now);
 	}
 
@@ -418,36 +419,30 @@ static void rxrpc_connection_reaper(struct work_struct *work)
  * preemptively destroy all the service connection records rather than
  * waiting for them to time out
  */
-void __exit rxrpc_destroy_all_connections(void)
+void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet)
 {
 	struct rxrpc_connection *conn, *_p;
 	bool leak = false;
 
 	_enter("");
 
-	rxrpc_destroy_all_client_connections();
+	rxrpc_destroy_all_client_connections(rxnet);
 
 	rxrpc_connection_expiry = 0;
-	cancel_delayed_work(&rxrpc_connection_reap);
-	rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0);
+	cancel_delayed_work(&rxnet->client_conn_reaper);
+	rxrpc_queue_delayed_work(&rxnet->client_conn_reaper, 0);
 	flush_workqueue(rxrpc_workqueue);
 
-	write_lock(&rxrpc_connection_lock);
-	list_for_each_entry_safe(conn, _p, &rxrpc_connections, link) {
+	write_lock(&rxnet->conn_lock);
+	list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) {
 		pr_err("AF_RXRPC: Leaked conn %p {%d}\n",
 		       conn, atomic_read(&conn->usage));
 		leak = true;
 	}
-	write_unlock(&rxrpc_connection_lock);
+	write_unlock(&rxnet->conn_lock);
 	BUG_ON(leak);
 
-	ASSERT(list_empty(&rxrpc_connection_proc_list));
-
-	/* Make sure the local and peer records pinned by any dying connections
-	 * are released.
-	 */
-	rcu_barrier();
-	rxrpc_destroy_client_conn_ids();
+	ASSERT(list_empty(&rxnet->conn_proc_list));
 
 	_leave("");
 }