net/smc: Reset conn->lgr when link group registration fails

[ Upstream commit 36595d8ad4 ]

SMC connections might fail to be registered in a link group due to
unable to find a usable link during its creation. As a result,
smc_conn_create() will return a failure and most resources related
to the connection won't be applied or initialized, such as
conn->abort_work or conn->lnk.

If smc_conn_free() is invoked later, it will try to access the
uninitialized resources related to the connection, thus causing
a warning or crash.

This patch tries to fix this by resetting conn->lgr to NULL if an
abnormal exit occurs in smc_lgr_register_conn(), thus avoiding the
access to uninitialized resources in smc_conn_free().

Meanwhile, the new created link group should be terminated if smc
connections can't be registered in it. So smc_lgr_cleanup_early() is
modified to take care of link group only and invoked to terminate
unusable link group by smc_conn_create(). The call to smc_conn_free()
is moved out from smc_lgr_cleanup_early() to smc_conn_abort().

Fixes: 56bc3b2094 ("net/smc: assign link to a new connection")
Suggested-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>

net/smc/af_smc.c

@@ -613,10 +613,12 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code,
 
 static void smc_conn_abort(struct smc_sock *smc, int local_first)
 {
+	struct smc_connection *conn = &smc->conn;
+	struct smc_link_group *lgr = conn->lgr;
+
+	smc_conn_free(conn);
 	if (local_first)
-		smc_lgr_cleanup_early(&smc->conn);
-	else
-		smc_conn_free(&smc->conn);
+		smc_lgr_cleanup_early(lgr);
 }
 
 /* check if there is a rdma device available for this connection. */

net/smc/smc_core.c

@@ -170,8 +170,10 @@ static int smc_lgr_register_conn(struct smc_connection *conn, bool first)
 
 	if (!conn->lgr->is_smcd) {
 		rc = smcr_lgr_conn_assign_link(conn, first);
-		if (rc)
+		if (rc) {
+			conn->lgr = NULL;
 			return rc;
+		}
 	}
 	/* find a new alert_token_local value not yet used by some connection
 	 * in this link group
@@ -579,15 +581,13 @@ int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-void smc_lgr_cleanup_early(struct smc_connection *conn)
+void smc_lgr_cleanup_early(struct smc_link_group *lgr)
 {
-	struct smc_link_group *lgr = conn->lgr;
 	spinlock_t *lgr_lock;
 
 	if (!lgr)
 		return;
 
-	smc_conn_free(conn);
 	smc_lgr_list_head(lgr, &lgr_lock);
 	spin_lock_bh(lgr_lock);
 	/* do not use this link group for new connections */
@@ -1750,8 +1750,10 @@ create:
 		write_lock_bh(&lgr->conns_lock);
 		rc = smc_lgr_register_conn(conn, true);
 		write_unlock_bh(&lgr->conns_lock);
-		if (rc)
+		if (rc) {
+			smc_lgr_cleanup_early(lgr);
 			goto out;
+		}
 	}
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;

net/smc/smc_core.h

@@ -419,7 +419,7 @@ static inline void smc_set_pci_values(struct pci_dev *pci_dev,
 struct smc_sock;
 struct smc_clc_msg_accept_confirm;
 
-void smc_lgr_cleanup_early(struct smc_connection *conn);
+void smc_lgr_cleanup_early(struct smc_link_group *lgr);
 void smc_lgr_terminate_sched(struct smc_link_group *lgr);
 void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport);
 void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport);