mlxsw: core: Fix race condition in __mlxsw_emad_transmit

Under certain conditions EMAD responses can be returned from the device
even before setting trans_active. This will cause the EMAD Rx listener
to drop the EMAD response - as there are no active transactions - and
timeouts will be generated.

Fix this by setting trans_active before transmitting the EMAD skb.

Fixes: 4ec14b7634b2 ("mlxsw: Add interface to access registers and process events")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index dbcaf5df8967e828f85648de4edce281860f2a61..28c19cc1a17c5f44a7b15103ce168651502843d8 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -374,26 +374,31 @@ static int __mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
        int err;
        int ret;
 
+       mlxsw_core->emad.trans_active = true;
+
        err = mlxsw_core_skb_transmit(mlxsw_core->driver_priv, skb, tx_info);
        if (err) {
                dev_err(mlxsw_core->bus_info->dev, "Failed to transmit EMAD (tid=%llx)\n",
                        mlxsw_core->emad.tid);
                dev_kfree_skb(skb);
-               return err;
+               goto trans_inactive_out;
        }
 
-       mlxsw_core->emad.trans_active = true;
        ret = wait_event_timeout(mlxsw_core->emad.wait,
                                 !(mlxsw_core->emad.trans_active),
                                 msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS));
        if (!ret) {
                dev_warn(mlxsw_core->bus_info->dev, "EMAD timed-out (tid=%llx)\n",
                         mlxsw_core->emad.tid);
-               mlxsw_core->emad.trans_active = false;
-               return -EIO;
+               err = -EIO;
+               goto trans_inactive_out;
        }
 
        return 0;
+
+trans_inactive_out:
+       mlxsw_core->emad.trans_active = false;
+       return err;
 }
 
 static int mlxsw_emad_process_status(struct mlxsw_core *mlxsw_core,