[PATCH AUTOSEL 5.6 082/149] RDMA/hns: Add the workqueue framework for flush cqe handler

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Yixian Liu <liuyixian@xxxxxxxxxx>

[ Upstream commit ffd541d45726341c1830ff595fd7352b6d1cfbcd ]

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/

Link: https://lore.kernel.org/r/1580983005-13899-2-git-send-email-liuyixian@xxxxxxxxxx
Signed-off-by: Yixian Liu <liuyixian@xxxxxxxxxx>
Reviewed-by: Salil Mehta <salil.mehta@xxxxxxxxxx>
Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/infiniband/hw/hns/hns_roce_device.h | 20 ++++++-----
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c  |  3 +-
 drivers/infiniband/hw/hns/hns_roce_qp.c     | 37 +++++++++++++++++++++
 3 files changed, 49 insertions(+), 11 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index a7c4ff975c289..a089d47354391 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -641,6 +641,15 @@ struct hns_roce_rinl_buf {
 	u32			 wqe_cnt;
 };
 
+struct hns_roce_work {
+	struct hns_roce_dev *hr_dev;
+	struct work_struct work;
+	u32 qpn;
+	u32 cqn;
+	int event_type;
+	int sub_type;
+};
+
 struct hns_roce_qp {
 	struct ib_qp		ibqp;
 	struct hns_roce_buf	hr_buf;
@@ -684,6 +693,7 @@ struct hns_roce_qp {
 	struct hns_roce_sge	sge;
 	u32			next_sge;
 
+	struct hns_roce_work	flush_work;
 	struct hns_roce_rinl_buf rq_inl_buf;
 	struct list_head	node;		/* all qps are on a list */
 	struct list_head	rq_node;	/* all recv qps are on a list */
@@ -906,15 +916,6 @@ struct hns_roce_caps {
 	u16		default_ceq_arm_st;
 };
 
-struct hns_roce_work {
-	struct hns_roce_dev *hr_dev;
-	struct work_struct work;
-	u32 qpn;
-	u32 cqn;
-	int event_type;
-	int sub_type;
-};
-
 struct hns_roce_dfx_hw {
 	int (*query_cqc_info)(struct hns_roce_dev *hr_dev, u32 cqn,
 			      int *buffer);
@@ -1237,6 +1238,7 @@ 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 12c4cd8e9378c..950c604a6fcb4 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -6292,8 +6292,7 @@ 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_ordered_workqueue("hns_roce_irq_workq", 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 3257ad11be482..dab73140c5c29 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -43,6 +43,43 @@
 
 #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 = container_of(flush_work,
+					struct hns_roce_qp, flush_work);
+	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);
+
+	/*
+	 * 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_work *flush_work = &hr_qp->flush_work;
+
+	flush_work->hr_dev = hr_dev;
+	INIT_WORK(&flush_work->work, flush_work_handle);
+	atomic_inc(&hr_qp->refcount);
+	queue_work(hr_dev->irq_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;
-- 
2.20.1




[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux