rds: tcp: use rds_destroy_pending() to synchronize netns/module teardown and rds connection/workq management

An rds_connection can get added during netns deletion between lines 528
and 529 of

  506 static void rds_tcp_kill_sock(struct net *net)
  :
  /* code to pull out all the rds_connections that should be destroyed */
  :
  528         spin_unlock_irq(&rds_tcp_conn_lock);
  529         list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node)
  530                 rds_conn_destroy(tc->t_cpath->cp_conn);

Such an rds_connection would miss out the rds_conn_destroy()
loop (that cancels all pending work) and (if it was scheduled
after netns deletion) could trigger the use-after-free.

A similar race-window exists for the module unload path
in rds_tcp_exit -> rds_tcp_destroy_conns

Concurrency with netns deletion (rds_tcp_kill_sock()) must be handled
by checking check_net() before enqueuing new work or adding new
connections.

Concurrency with module-unload is handled by maintaining a module
specific flag that is set at the start of the module exit function,
and must be checked before enqueuing new work or adding new connections.

This commit refactors existing RDS_DESTROY_PENDING checks added by
commit 3db6e0d172c9 ("rds: use RCU to synchronize work-enqueue with
connection teardown") and consolidates all the concurrency checks
listed above into the function rds_destroy_pending().

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 5 insertions, 5 deletions

diff --git a/net/rds/send.c b/net/rds/send.c
index d3e32d1f3c7d..b1b0022b8370 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -162,7 +162,7 @@ restart:
 		goto out;
 	}
 
-	if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) {
+	if (rds_destroy_pending(cp->cp_conn)) {
 		release_in_xmit(cp);
 		ret = -ENETUNREACH; /* dont requeue send work */
 		goto out;
@@ -444,7 +444,7 @@ over_batch:
 			if (batch_count < send_batch_count)
 				goto restart;
 			rcu_read_lock();
-			if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+			if (rds_destroy_pending(cp->cp_conn))
 				ret = -ENETUNREACH;
 			else
 				queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
@@ -1162,7 +1162,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	else
 		cpath = &conn->c_path[0];
 
-	if (test_bit(RDS_DESTROY_PENDING, &cpath->cp_flags)) {
+	if (rds_destroy_pending(conn)) {
 		ret = -EAGAIN;
 		goto out;
 	}
@@ -1209,7 +1209,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	if (ret == -ENOMEM || ret == -EAGAIN) {
 		ret = 0;
 		rcu_read_lock();
-		if (test_bit(RDS_DESTROY_PENDING, &cpath->cp_flags))
+		if (rds_destroy_pending(cpath->cp_conn))
 			ret = -ENETUNREACH;
 		else
 			queue_delayed_work(rds_wq, &cpath->cp_send_w, 1);
@@ -1295,7 +1295,7 @@ rds_send_probe(struct rds_conn_path *cp, __be16 sport,
 
 	/* schedule the send work on rds_wq */
 	rcu_read_lock();
-	if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+	if (!rds_destroy_pending(cp->cp_conn))
 		queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
 	rcu_read_unlock();