Re: [PATCH v2 for-next 1/2] RDMA/hns: Add the workqueue framework for flush cqe handler

[Jason Gunthorpe <jgg@ziepe.ca>]

On Tue, Nov 12, 2019 at 08:52:03PM +0800, Yixian Liu wrote:
> HiP08 RoCE hardware lacks ability(a known hardware problem) to flush
> outstanding WQEs if QP state gets into errored mode for some reason.
> To overcome this hardware problem and as a workaround, when QP is
> detected to be in errored state during various legs like post send,
> post receive etc [1], flush needs to be performed from the driver.
> 
> The earlier patch[1] sent to solve the hardware limitation explained
> in the cover-letter had a bug in the software flushing leg. It
> acquired mutex while modifying QP state to errored state and while
> conveying it to the hardware using the mailbox. This caused leg to
> sleep while holding spin-lock and caused crash.
> 
> Suggested Solution:
> we have proposed to defer the flushing of the QP in the Errored state
> using the workqueue to get around with the limitation of our hardware.
> 
> This patch adds the framework of the workqueue and the flush handler
> function.
> 
> [1] https://patchwork.kernel.org/patch/10534271/
> 
> Signed-off-by: Yixian Liu <liuyixian@huawei.com>
> Reviewed-by: Salil Mehta <salil.mehta@huawei.com>
>  drivers/infiniband/hw/hns/hns_roce_device.h |  3 +++
>  drivers/infiniband/hw/hns/hns_roce_hw_v2.c  |  4 ++--
>  drivers/infiniband/hw/hns/hns_roce_qp.c     | 33 +++++++++++++++++++++++++++++
>  3 files changed, 38 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
> index a1b712e..42d8a5a 100644
> +++ b/drivers/infiniband/hw/hns/hns_roce_device.h
> @@ -906,6 +906,7 @@ struct hns_roce_caps {
>  struct hns_roce_work {
>  	struct hns_roce_dev *hr_dev;
>  	struct work_struct work;
> +	struct hns_roce_qp *hr_qp;
>  	u32 qpn;
>  	u32 cqn;
>  	int event_type;
> @@ -1034,6 +1035,7 @@ struct hns_roce_dev {
>  	const struct hns_roce_hw *hw;
>  	void			*priv;
>  	struct workqueue_struct *irq_workq;
> +	struct hns_roce_work flush_work;
>  	const struct hns_roce_dfx_hw *dfx;
>  };
>  
> @@ -1226,6 +1228,7 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *ib_pd,
>  				 struct ib_udata *udata);
>  int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
>  		       int attr_mask, struct ib_udata *udata);
> +void init_flush_work(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp);
>  void *get_recv_wqe(struct hns_roce_qp *hr_qp, int n);
>  void *get_send_wqe(struct hns_roce_qp *hr_qp, int n);
>  void *get_send_extend_sge(struct hns_roce_qp *hr_qp, int n);
> diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
> index 907c951..ec48e7e 100644
> +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
> @@ -5967,8 +5967,8 @@ static int hns_roce_v2_init_eq_table(struct hns_roce_dev *hr_dev)
>  		goto err_request_irq_fail;
>  	}
>  
> -	hr_dev->irq_workq =
> -		create_singlethread_workqueue("hns_roce_irq_workqueue");
> +	hr_dev->irq_workq = alloc_workqueue("hns_roce_irq_workqueue",
> +					    WQ_MEM_RECLAIM, 0);
>  	if (!hr_dev->irq_workq) {
>  		dev_err(dev, "Create irq workqueue failed!\n");
>  		ret = -ENOMEM;
> diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
> index 9442f01..0111f2e 100644
> +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
> @@ -43,6 +43,39 @@
>  
>  #define SQP_NUM				(2 * HNS_ROCE_MAX_PORTS)
>  
> +static void flush_work_handle(struct work_struct *work)
> +{
> +	struct hns_roce_work *flush_work = container_of(work,
> +					struct hns_roce_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);
> +
> +	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_work *flush_work = &hr_dev->flush_work;
> +
> +	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->irq_workq, &flush_work->work);

It kind of looks like this can be called multiple times? It won't work
right unless it is called exactly once

Jason