Sorry. The patch is to the CM. Subject was changed

On Wed, Mar 2, 2011 at 5:45 PM, Moni Shoua <[email protected]> wrote:
>
> When destroying a cm_id from a context of a work queue and if the lap_state of
> this cm_id is IB_CM_LAP_SENT, we need to release the reference of this id that
> was taken upon the send of the lap message.  Otherwise, if the expected apr
> message gets lost, it is only after a long time that the reference will be
> released, while during that the work handler thread is not available to 
> process
> other things.
> Also, a sigle variable 'msg' was used to hold the last snet mad. However, this
> variable serves 2 state machines (CM and LAP) which can cause to memory leaks 
> or
> to unexpected behavior. This patch adds another variable to hold the lap mad.
>
> Signed-off-by: Moni Shoua <[email protected]>
> Signed-off-by: Amir Vadai <[email protected]>
> --
>  drivers/infiniband/core/cm.c |   25 ++++++++++++++++++++++---
>  1 file changed, 22 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
> index 64e0903..3c00646 100644
> --- a/drivers/infiniband/core/cm.c
> +++ b/drivers/infiniband/core/cm.c
> @@ -210,6 +210,7 @@ struct cm_id_private {
>        atomic_t refcount;
>
>        struct ib_mad_send_buf *msg;
> +       struct ib_mad_send_buf *lap_msg;
>        struct cm_timewait_info *timewait_info;
>        /* todo: use alternate port on send failure */
>        struct cm_av av;
> @@ -839,6 +840,24 @@ static void cm_destroy_id(struct ib_cm_id *cm_id, int 
> err)
>        cm_id_priv = container_of(cm_id, struct cm_id_private, id);
>  retest:
>        spin_lock_irq(&cm_id_priv->lock);
> +
> +       /* handle lap states first */
> +       switch (cm_id->lap_state) {
> +       case IB_CM_LAP_UNINIT:
> +       case IB_CM_LAP_IDLE:
> +               break;
> +       case IB_CM_LAP_SENT:
> +               cm_id_priv->id.lap_state = IB_CM_LAP_IDLE;
> +               ib_cancel_mad(cm_id_priv->av.port->mad_agent, 
> cm_id_priv->lap_msg);
> +               cm_id_priv->lap_msg = NULL;
> +               break;
> +       case IB_CM_LAP_RCVD:
> +       case IB_CM_MRA_LAP_SENT:
> +       case IB_CM_MRA_LAP_RCVD:
> +       default:
> +               break;
> +       }
> +
>        switch (cm_id->state) {
>        case IB_CM_LISTEN:
>                cm_id->state = IB_CM_IDLE;
> @@ -2615,7 +2634,7 @@ int ib_send_cm_lap(struct ib_cm_id *cm_id,
>        }
>
>        cm_id->lap_state = IB_CM_LAP_SENT;
> -       cm_id_priv->msg = msg;
> +       cm_id_priv->lap_msg = msg;
>
>  out:   spin_unlock_irqrestore(&cm_id_priv->lock, flags);
>        return ret;
> @@ -2811,8 +2830,8 @@ static int cm_apr_handler(struct cm_work *work)
>                goto out;
>        }
>        cm_id_priv->id.lap_state = IB_CM_LAP_IDLE;
> -       ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
> -       cm_id_priv->msg = NULL;
> +       ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->lap_msg);
> +       cm_id_priv->lap_msg = NULL;
>
>        ret = atomic_inc_and_test(&cm_id_priv->work_count);
>        if (!ret)
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to [email protected]
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to