On Mon, Oct 28, 2019 at 05:45:44PM +0800, Yixian Liu wrote:
> @@ -1998,6 +2000,17 @@ static int hns_roce_v2_init(struct hns_roce_dev *hr_dev)
> }
> }
>
> + snprintf(workq_name, HNS_ROCE_WORKQ_NAME_LEN - 1,
> + "hns_roce_%d_flush_wq", device_id);
> + device_id++;
> +
> + hr_dev->flush_workq = alloc_workqueue(workq_name, WQ_HIGHPRI, 0);
> + if (!hr_dev->flush_workq) {
Why is this so time critical?
> diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
> index bec48f2..2c8f726 100644
> +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
> @@ -43,6 +43,49 @@
>
> #define SQP_NUM (2 * HNS_ROCE_MAX_PORTS)
>
> +static void flush_work_handle(struct work_struct *work)
> +{
> + struct hns_roce_flush_work *flush_work = container_of(work,
> + struct hns_roce_flush_work, work);
> + struct hns_roce_qp *hr_qp = flush_work->hr_qp;
> + struct device *dev = flush_work->hr_dev->dev;
> + struct ib_qp_attr attr;
> + int attr_mask;
> + int ret;
> +
> + attr_mask = IB_QP_STATE;
> + attr.qp_state = IB_QPS_ERR;
> +
> + ret = hns_roce_modify_qp(&hr_qp->ibqp, &attr, attr_mask, NULL);
> + if (ret)
> + dev_err(dev, "Modify QP to error state failed(%d) during CQE flush\n",
> + ret);
There is something wrong with your description as all this seems to do
is tell the HW to go to the ERR state.
Why don't you do this from hns_roce_irq_work_handle() ?
> + kfree(flush_work);
> +
> + /*
> + * make sure we signal QP destroy leg that flush QP was completed
> + * so that it can safely proceed ahead now and destroy QP
> + */
> + if (atomic_dec_and_test(&hr_qp->refcount))
> + complete(&hr_qp->free);
> +}
> +
> +void init_flush_work(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp)
> +{
> + struct hns_roce_flush_work *flush_work;
> +
> + flush_work = kzalloc(sizeof(struct hns_roce_flush_work), GFP_ATOMIC);
> + if (!flush_work)
> + return;
Don't do things that can fail here
> +
> + flush_work->hr_dev = hr_dev;
> + flush_work->hr_qp = hr_qp;
> + INIT_WORK(&flush_work->work, flush_work_handle);
> + atomic_inc(&hr_qp->refcount);
> + queue_work(hr_dev->flush_workq, &flush_work->work);
> +}
> +
> void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type)
> {
> struct device *dev = hr_dev->dev;
