RDMA/mana_ib: Process QP error events in mana_ib

Process QP fatal events from the error event queue.
For that, find the QP, using QPN from the event, and then call its
event_handler. To find the QPs, store created RC QPs in an xarray.

Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
Link: https://lore.kernel.org/r/1717754897-19858-1-git-send-email-kotaranov@linux.microsoft.com
Reviewed-by: Wei Hu <weh@microsoft.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>

drivers/infiniband/hw/mana/device.c

@@ -126,6 +126,7 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	if (ret)
 		goto destroy_eqs;
 
+	xa_init_flags(&dev->qp_table_wq, XA_FLAGS_LOCK_IRQ);
 	ret = mana_ib_gd_config_mac(dev, ADDR_OP_ADD, mac_addr);
 	if (ret) {
 		ibdev_err(&dev->ib_dev, "Failed to add Mac address, ret %d",
@@ -143,6 +144,7 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	return 0;
 
 destroy_rnic:
+	xa_destroy(&dev->qp_table_wq);
 	mana_ib_gd_destroy_rnic_adapter(dev);
 destroy_eqs:
 	mana_ib_destroy_eqs(dev);
@@ -158,6 +160,7 @@ static void mana_ib_remove(struct auxiliary_device *adev)
 	struct mana_ib_dev *dev = dev_get_drvdata(&adev->dev);
 
 	ib_unregister_device(&dev->ib_dev);
+	xa_destroy(&dev->qp_table_wq);
 	mana_ib_gd_destroy_rnic_adapter(dev);
 	mana_ib_destroy_eqs(dev);
 	mana_gd_deregister_device(dev->gdma_dev);

drivers/infiniband/hw/mana/main.c

@@ -667,6 +667,33 @@ int mana_ib_gd_query_adapter_caps(struct mana_ib_dev *dev)
 	return 0;
 }
 
+static void
+mana_ib_event_handler(void *ctx, struct gdma_queue *q, struct gdma_event *event)
+{
+	struct mana_ib_dev *mdev = (struct mana_ib_dev *)ctx;
+	struct mana_ib_qp *qp;
+	struct ib_event ev;
+	u32 qpn;
+
+	switch (event->type) {
+	case GDMA_EQE_RNIC_QP_FATAL:
+		qpn = event->details[0];
+		qp = mana_get_qp_ref(mdev, qpn);
+		if (!qp)
+			break;
+		if (qp->ibqp.event_handler) {
+			ev.device = qp->ibqp.device;
+			ev.element.qp = &qp->ibqp;
+			ev.event = IB_EVENT_QP_FATAL;
+			qp->ibqp.event_handler(&ev, qp->ibqp.qp_context);
+		}
+		mana_put_qp_ref(qp);
+		break;
+	default:
+		break;
+	}
+}
+
 int mana_ib_create_eqs(struct mana_ib_dev *mdev)
 {
 	struct gdma_context *gc = mdev_to_gc(mdev);
@@ -676,7 +703,7 @@ int mana_ib_create_eqs(struct mana_ib_dev *mdev)
 	spec.type = GDMA_EQ;
 	spec.monitor_avl_buf = false;
 	spec.queue_size = EQ_SIZE;
-	spec.eq.callback = NULL;
+	spec.eq.callback = mana_ib_event_handler;
 	spec.eq.context = mdev;
 	spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE;
 	spec.eq.msix_index = 0;
@@ -691,7 +718,7 @@ int mana_ib_create_eqs(struct mana_ib_dev *mdev)
 		err = -ENOMEM;
 		goto destroy_fatal_eq;
 	}
-
+	spec.eq.callback = NULL;
 	for (i = 0; i < mdev->ib_dev.num_comp_vectors; i++) {
 		spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
 		err = mana_gd_create_mana_eq(mdev->gdma_dev, &spec, &mdev->eqs[i]);

drivers/infiniband/hw/mana/mana_ib.h

@@ -62,6 +62,7 @@ struct mana_ib_dev {
 	mana_handle_t adapter_handle;
 	struct gdma_queue *fatal_err_eq;
 	struct gdma_queue **eqs;
+	struct xarray qp_table_wq;
 	struct mana_ib_adapter_caps adapter_caps;
 };
 
@@ -124,6 +125,9 @@ struct mana_ib_qp {
 
 	/* The port on the IB device, starting with 1 */
 	u32 port;
+
+	refcount_t		refcount;
+	struct completion	free;
 };
 
 struct mana_ib_ucontext {
@@ -333,6 +337,26 @@ static inline struct gdma_context *mdev_to_gc(struct mana_ib_dev *mdev)
 	return mdev->gdma_dev->gdma_context;
 }
 
+static inline struct mana_ib_qp *mana_get_qp_ref(struct mana_ib_dev *mdev,
+						 uint32_t qid)
+{
+	struct mana_ib_qp *qp;
+	unsigned long flag;
+
+	xa_lock_irqsave(&mdev->qp_table_wq, flag);
+	qp = xa_load(&mdev->qp_table_wq, qid);
+	if (qp)
+		refcount_inc(&qp->refcount);
+	xa_unlock_irqrestore(&mdev->qp_table_wq, flag);
+	return qp;
+}
+
+static inline void mana_put_qp_ref(struct mana_ib_qp *qp)
+{
+	if (refcount_dec_and_test(&qp->refcount))
+		complete(&qp->free);
+}
+
 static inline struct net_device *mana_ib_get_netdev(struct ib_device *ibdev, u32 port)
 {
 	struct mana_ib_dev *mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);

drivers/infiniband/hw/mana/qp.c

@@ -398,6 +398,22 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
 	return err;
 }
 
+static int mana_table_store_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp)
+{
+	refcount_set(&qp->refcount, 1);
+	init_completion(&qp->free);
+	return xa_insert_irq(&mdev->qp_table_wq, qp->ibqp.qp_num, qp,
+			     GFP_KERNEL);
+}
+
+static void mana_table_remove_qp(struct mana_ib_dev *mdev,
+				 struct mana_ib_qp *qp)
+{
+	xa_erase_irq(&mdev->qp_table_wq, qp->ibqp.qp_num);
+	mana_put_qp_ref(qp);
+	wait_for_completion(&qp->free);
+}
+
 static int mana_ib_create_rc_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
 				struct ib_qp_init_attr *attr, struct ib_udata *udata)
 {
@@ -460,6 +476,10 @@ static int mana_ib_create_rc_qp(struct ib_qp *ibqp, struct ib_pd *ibpd,
 		}
 	}
 
+	err = mana_table_store_qp(mdev, qp);
+	if (err)
+		goto destroy_qp;
+
 	return 0;
 
 destroy_qp:
@@ -620,6 +640,8 @@ static int mana_ib_destroy_rc_qp(struct mana_ib_qp *qp, struct ib_udata *udata)
 		container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
 	int i;
 
+	mana_table_remove_qp(mdev, qp);
+
 	/* Ignore return code as there is not much we can do about it.
 	 * The error message is printed inside.
 	 */

drivers/net/ethernet/microsoft/mana/gdma_main.c

@@ -380,6 +380,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 	case GDMA_EQE_HWC_INIT_EQ_ID_DB:
 	case GDMA_EQE_HWC_INIT_DATA:
 	case GDMA_EQE_HWC_INIT_DONE:
+	case GDMA_EQE_RNIC_QP_FATAL:
 		if (!eq->eq.callback)
 			break;
 

include/net/mana/gdma.h

@@ -60,6 +60,7 @@ enum gdma_eqe_type {
 	GDMA_EQE_HWC_INIT_DONE		= 131,
 	GDMA_EQE_HWC_SOC_RECONFIG	= 132,
 	GDMA_EQE_HWC_SOC_RECONFIG_DATA	= 133,
+	GDMA_EQE_RNIC_QP_FATAL		= 176,
 };
 
 enum {