On Tue, Nov 14, 2017 at 2:51 PM, Leon Romanovsky <leon@xxxxxxxxxx> wrote:
> From: Daniel Jurgens <danielj@xxxxxxxxxxxx>
>
> Add debug prints to the error paths in the connection manager control
> flows, to help debug connection management problems.
Sean, the CM author and maintainer since 2.6.12/13 (12 years) is not copied
>
> Signed-off-by: Daniel Jurgens <danielj@xxxxxxxxxxxx>
> Signed-off-by: Leon Romanovsky <leon@xxxxxxxxxx>
> ---
> drivers/infiniband/core/cm.c | 51 ++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 51 insertions(+)
>
> diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
> index fe7a5e0d79b0..cbb385e02947 100644
> --- a/drivers/infiniband/core/cm.c
> +++ b/drivers/infiniband/core/cm.c
> @@ -1841,6 +1841,8 @@ static int cm_req_handler(struct cm_work *work)
>
> listen_cm_id_priv = cm_match_req(work, cm_id_priv);
> if (!listen_cm_id_priv) {
> + pr_debug("%s: local_id %d, no listen_cm_id_priv\n", __func__,
> + be32_to_cpu(cm_id->local_id));
> ret = -EINVAL;
> goto free_timeinfo;
> }
> @@ -1998,6 +2000,8 @@ int ib_send_cm_rep(struct ib_cm_id *cm_id,
> spin_lock_irqsave(&cm_id_priv->lock, flags);
> if (cm_id->state != IB_CM_REQ_RCVD &&
> cm_id->state != IB_CM_MRA_REQ_SENT) {
> + pr_debug("%s: local_comm_id %d, cm_id->state: %d\n", __func__,
> + be32_to_cpu(cm_id_priv->id.local_id), cm_id->state);
> ret = -EINVAL;
> goto out;
> }
> @@ -2064,6 +2068,8 @@ int ib_send_cm_rtu(struct ib_cm_id *cm_id,
> spin_lock_irqsave(&cm_id_priv->lock, flags);
> if (cm_id->state != IB_CM_REP_RCVD &&
> cm_id->state != IB_CM_MRA_REP_SENT) {
> + pr_debug("%s: local_id %d, cm_id->state %d\n", __func__,
> + be32_to_cpu(cm_id->local_id), cm_id->state);
> ret = -EINVAL;
> goto error;
> }
> @@ -2171,6 +2177,8 @@ static int cm_rep_handler(struct cm_work *work)
> cm_id_priv = cm_acquire_id(rep_msg->remote_comm_id, 0);
> if (!cm_id_priv) {
> cm_dup_rep_handler(work);
> + pr_debug("%s: remote_comm_id %d, no cm_id_priv\n", __func__,
> + be32_to_cpu(rep_msg->remote_comm_id));
> return -EINVAL;
> }
>
> @@ -2184,6 +2192,10 @@ static int cm_rep_handler(struct cm_work *work)
> default:
> spin_unlock_irq(&cm_id_priv->lock);
> ret = -EINVAL;
> + pr_debug("%s: cm_id_priv->id.state: %d, local_comm_id %d, remote_comm_id %d\n",
> + __func__, cm_id_priv->id.state,
> + be32_to_cpu(rep_msg->local_comm_id),
> + be32_to_cpu(rep_msg->remote_comm_id));
> goto error;
> }
>
> @@ -2197,6 +2209,8 @@ static int cm_rep_handler(struct cm_work *work)
> spin_unlock(&cm.lock);
> spin_unlock_irq(&cm_id_priv->lock);
> ret = -EINVAL;
> + pr_debug("%s: Failed to insert remote id %d\n", __func__,
> + be32_to_cpu(rep_msg->remote_comm_id));
> goto error;
> }
> /* Check for a stale connection. */
> @@ -2214,6 +2228,10 @@ static int cm_rep_handler(struct cm_work *work)
> IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REP,
> NULL, 0);
> ret = -EINVAL;
> + pr_debug("%s: Stale connection. local_comm_id %d, remote_comm_id %d\n",
> + __func__, be32_to_cpu(rep_msg->local_comm_id),
> + be32_to_cpu(rep_msg->remote_comm_id));
> +
> if (cur_cm_id_priv) {
> cm_id = &cur_cm_id_priv->id;
> ib_send_cm_dreq(cm_id, NULL, 0);
> @@ -2360,6 +2378,8 @@ int ib_send_cm_dreq(struct ib_cm_id *cm_id,
> cm_id_priv = container_of(cm_id, struct cm_id_private, id);
> spin_lock_irqsave(&cm_id_priv->lock, flags);
> if (cm_id->state != IB_CM_ESTABLISHED) {
> + pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
> + be32_to_cpu(cm_id->local_id), cm_id->state);
> ret = -EINVAL;
> goto out;
> }
> @@ -2429,6 +2449,8 @@ int ib_send_cm_drep(struct ib_cm_id *cm_id,
> if (cm_id->state != IB_CM_DREQ_RCVD) {
> spin_unlock_irqrestore(&cm_id_priv->lock, flags);
> kfree(data);
> + pr_debug("%s: local_id %d, cm_idcm_id->state(%d) != IB_CM_DREQ_RCVD\n",
> + __func__, be32_to_cpu(cm_id->local_id), cm_id->state);
> return -EINVAL;
> }
>
> @@ -2494,6 +2516,9 @@ static int cm_dreq_handler(struct cm_work *work)
> atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
> counter[CM_DREQ_COUNTER]);
> cm_issue_drep(work->port, work->mad_recv_wc);
> + pr_debug("%s: no cm_id_priv, local_comm_id %d, remote_comm_id %d\n",
> + __func__, be32_to_cpu(dreq_msg->local_comm_id),
> + be32_to_cpu(dreq_msg->remote_comm_id));
> return -EINVAL;
> }
>
> @@ -2536,6 +2561,9 @@ static int cm_dreq_handler(struct cm_work *work)
> counter[CM_DREQ_COUNTER]);
> goto unlock;
> default:
> + pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
> + __func__, be32_to_cpu(cm_id_priv->id.local_id),
> + cm_id_priv->id.state);
> goto unlock;
> }
> cm_id_priv->id.state = IB_CM_DREQ_RCVD;
> @@ -2639,6 +2667,8 @@ int ib_send_cm_rej(struct ib_cm_id *cm_id,
> cm_enter_timewait(cm_id_priv);
> break;
> default:
> + pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
> + be32_to_cpu(cm_id_priv->id.local_id), cm_id->state);
> ret = -EINVAL;
> goto out;
> }
> @@ -2749,6 +2779,9 @@ static int cm_rej_handler(struct cm_work *work)
> /* fall through */
> default:
> spin_unlock_irq(&cm_id_priv->lock);
> + pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
> + __func__, be32_to_cpu(cm_id_priv->id.local_id),
> + cm_id_priv->id.state);
> ret = -EINVAL;
> goto out;
> }
> @@ -2812,6 +2845,9 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
> }
> /* fall through */
> default:
> + pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
> + __func__, be32_to_cpu(cm_id_priv->id.local_id),
> + cm_id_priv->id.state);
> ret = -EINVAL;
> goto error1;
> }
> @@ -2913,6 +2949,9 @@ static int cm_mra_handler(struct cm_work *work)
> counter[CM_MRA_COUNTER]);
> /* fall through */
> default:
> + pr_debug("%s local_id %d, cm_id_priv->id.state: %d\n",
> + __func__, be32_to_cpu(cm_id_priv->id.local_id),
> + cm_id_priv->id.state);
> goto out;
> }
>
> @@ -3693,6 +3732,7 @@ static void cm_work_handler(struct work_struct *_work)
> ret = cm_timewait_handler(work);
> break;
> default:
> + pr_debug("cm_event.event: 0x%x\n", work->cm_event.event);
> ret = -EINVAL;
> break;
> }
> @@ -3728,6 +3768,8 @@ static int cm_establish(struct ib_cm_id *cm_id)
> ret = -EISCONN;
> break;
> default:
> + pr_debug("%s: local_id %d, cm_id->state: %d\n", __func__,
> + be32_to_cpu(cm_id->local_id), cm_id->state);
> ret = -EINVAL;
> break;
> }
> @@ -3925,6 +3967,9 @@ static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv,
> ret = 0;
> break;
> default:
> + pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
> + __func__, be32_to_cpu(cm_id_priv->id.local_id),
> + cm_id_priv->id.state);
> ret = -EINVAL;
> break;
> }
> @@ -3972,6 +4017,9 @@ static int cm_init_qp_rtr_attr(struct cm_id_private *cm_id_priv,
> ret = 0;
> break;
> default:
> + pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
> + __func__, be32_to_cpu(cm_id_priv->id.local_id),
> + cm_id_priv->id.state);
> ret = -EINVAL;
> break;
> }
> @@ -4031,6 +4079,9 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv,
> ret = 0;
> break;
> default:
> + pr_debug("%s: local_id %d, cm_id_priv->id.state: %d\n",
> + __func__, be32_to_cpu(cm_id_priv->id.local_id),
> + cm_id_priv->id.state);
> ret = -EINVAL;
> break;
> }
> --
> 2.15.0
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> 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 majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
