[rds-devel] [PATCH RFC net-next 3/6] rds: hold a sock ref from rds_message to the rds_sock

[Sowmini Varadhan]

The existing model holds a reference from the rds_sock to the
rds_message, but the rds_message does not itself hold a sock_put()
on the rds_sock. Instead the m_rs field in the rds_message is
assigned when the message is queued on the sock, and nulled when
the message is dequeued from the sock.

We want to be able to notify userspace when the rds_message
is actually freed (from rds_message_purge(), after the refcounts
to the rds_message go to 0). These notifications will signal that
it is safe for uspace to free/reuse any pages that may have
been pinned down for zerocopy, and are sent up on the PF_RDS
socket.

In order to be able to send the notifications on the rds_sock,
we need to retain the m_rs assignment in the rds_message with
the necessary refcount book-keeping.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan at oracle.com>
---
 net/rds/message.c |    8 +++++++-
 net/rds/send.c    |    7 +------
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/rds/message.c b/net/rds/message.c
index 4318cc9..ef3daaf 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -58,7 +58,7 @@ void rds_message_addref(struct rds_message *rm)
  */
 static void rds_message_purge(struct rds_message *rm)
 {
-	unsigned long i;
+	unsigned long i, flags;
 
 	if (unlikely(test_bit(RDS_MSG_PAGEVEC, &rm->m_flags)))
 		return;
@@ -69,6 +69,12 @@ static void rds_message_purge(struct rds_message *rm)
 		__free_page(sg_page(&rm->data.op_sg[i]));
 	}
 	rm->data.op_nents = 0;
+	spin_lock_irqsave(&rm->m_rs_lock, flags);
+	if (rm->m_rs) {
+		sock_put(rds_rs_to_sk(rm->m_rs));
+		rm->m_rs = NULL;
+	}
+	spin_unlock_irqrestore(&rm->m_rs_lock, flags);
 
 	if (rm->rdma.op_active)
 		rds_rdma_free_op(&rm->rdma);
diff --git a/net/rds/send.c b/net/rds/send.c
index d3e32d1..5ac0925 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -649,7 +649,6 @@ static void rds_send_remove_from_sock(struct list_head *messages, int status)
 				rm->rdma.op_notifier = NULL;
 			}
 			was_on_sock = 1;
-			rm->m_rs = NULL;
 		}
 		spin_unlock(&rs->rs_lock);
 
@@ -756,9 +755,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 		 */
 		if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) {
 			spin_unlock_irqrestore(&cp->cp_lock, flags);
-			spin_lock_irqsave(&rm->m_rs_lock, flags);
-			rm->m_rs = NULL;
-			spin_unlock_irqrestore(&rm->m_rs_lock, flags);
 			continue;
 		}
 		list_del_init(&rm->m_conn_item);
@@ -774,7 +770,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 		__rds_send_complete(rs, rm, RDS_RDMA_CANCELED);
 		spin_unlock(&rs->rs_lock);
 
-		rm->m_rs = NULL;
 		spin_unlock_irqrestore(&rm->m_rs_lock, flags);
 
 		rds_message_put(rm);
@@ -798,7 +793,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 		__rds_send_complete(rs, rm, RDS_RDMA_CANCELED);
 		spin_unlock(&rs->rs_lock);
 
-		rm->m_rs = NULL;
 		spin_unlock_irqrestore(&rm->m_rs_lock, flags);
 
 		rds_message_put(rm);
@@ -849,6 +843,7 @@ static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn,
 		list_add_tail(&rm->m_sock_item, &rs->rs_send_queue);
 		set_bit(RDS_MSG_ON_SOCK, &rm->m_flags);
 		rds_message_addref(rm);
+		sock_hold(rds_rs_to_sk(rs));
 		rm->m_rs = rs;
 
 		/* The code ordering is a little weird, but we're
-- 
1.7.1