IB/core: Add an unbound WQ type to the new CQ API

The upstream kernel commit cited below modified the workqueue in the
new CQ API to be bound to a specific CPU (instead of being unbound).
This caused ALL users of the new CQ API to use the same bound WQ.

Specifically, MAD handling was severely delayed when the CPU bound
to the WQ was busy handling (higher priority) interrupts.

This caused a delay in the MAD "heartbeat" response handling,
which resulted in ports being incorrectly classified as "down".

To fix this, add a new "unbound" WQ type to the new CQ API, so that users
have the option to choose either a bound WQ or an unbound WQ.

For MADs, choose the new "unbound" WQ.

Fixes: b7363e67 ("IB/device: Convert ib-comp-wq to be CPU-bound")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.m>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/core/cq.c

@@ -112,12 +112,12 @@ static void ib_cq_poll_work(struct work_struct *work)
 				    IB_POLL_BATCH);
 	if (completed >= IB_POLL_BUDGET_WORKQUEUE ||
 	    ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
-		queue_work(ib_comp_wq, &cq->work);
+		queue_work(cq->comp_wq, &cq->work);
 }
 
 static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 {
-	queue_work(ib_comp_wq, &cq->work);
+	queue_work(cq->comp_wq, &cq->work);
 }
 
 /**
@@ -175,9 +175,12 @@ struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private,
 		ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
 		break;
 	case IB_POLL_WORKQUEUE:
+	case IB_POLL_UNBOUND_WORKQUEUE:
 		cq->comp_handler = ib_cq_completion_workqueue;
 		INIT_WORK(&cq->work, ib_cq_poll_work);
 		ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
+		cq->comp_wq = (cq->poll_ctx == IB_POLL_WORKQUEUE) ?
+				ib_comp_wq : ib_comp_unbound_wq;
 		break;
 	default:
 		ret = -EINVAL;
@@ -213,6 +216,7 @@ void ib_free_cq(struct ib_cq *cq)
 		irq_poll_disable(&cq->iop);
 		break;
 	case IB_POLL_WORKQUEUE:
+	case IB_POLL_UNBOUND_WORKQUEUE:
 		cancel_work_sync(&cq->work);
 		break;
 	default:

drivers/infiniband/core/device.c

@@ -61,6 +61,7 @@ struct ib_client_data {
 };
 
 struct workqueue_struct *ib_comp_wq;
+struct workqueue_struct *ib_comp_unbound_wq;
 struct workqueue_struct *ib_wq;
 EXPORT_SYMBOL_GPL(ib_wq);
 
@@ -1166,10 +1167,19 @@ static int __init ib_core_init(void)
 		goto err;
 	}
 
+	ib_comp_unbound_wq =
+		alloc_workqueue("ib-comp-unb-wq",
+				WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM |
+				WQ_SYSFS, WQ_UNBOUND_MAX_ACTIVE);
+	if (!ib_comp_unbound_wq) {
+		ret = -ENOMEM;
+		goto err_comp;
+	}
+
 	ret = class_register(&ib_class);
 	if (ret) {
 		pr_warn("Couldn't create InfiniBand device class\n");
-		goto err_comp;
+		goto err_comp_unbound;
 	}
 
 	ret = rdma_nl_init();
@@ -1218,6 +1228,8 @@ static int __init ib_core_init(void)
 	rdma_nl_exit();
 err_sysfs:
 	class_unregister(&ib_class);
+err_comp_unbound:
+	destroy_workqueue(ib_comp_unbound_wq);
 err_comp:
 	destroy_workqueue(ib_comp_wq);
 err:
@@ -1236,6 +1248,7 @@ static void __exit ib_core_cleanup(void)
 	addr_cleanup();
 	rdma_nl_exit();
 	class_unregister(&ib_class);
+	destroy_workqueue(ib_comp_unbound_wq);
 	destroy_workqueue(ib_comp_wq);
 	/* Make sure that any pending umem accounting work is done. */
 	destroy_workqueue(ib_wq);

drivers/infiniband/core/mad.c

@@ -3183,7 +3183,7 @@ static int ib_mad_port_open(struct ib_device *device,
 		cq_size *= 2;
 
 	port_priv->cq = ib_alloc_cq(port_priv->device, port_priv, cq_size, 0,
-			IB_POLL_WORKQUEUE);
+			IB_POLL_UNBOUND_WORKQUEUE);
 	if (IS_ERR(port_priv->cq)) {
 		dev_err(&device->dev, "Couldn't create ib_mad CQ\n");
 		ret = PTR_ERR(port_priv->cq);

include/rdma/ib_verbs.h

@@ -71,6 +71,7 @@
 
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
+extern struct workqueue_struct *ib_comp_unbound_wq;
 
 union ib_gid {
 	u8	raw[16];
@@ -1573,6 +1574,7 @@ enum ib_poll_context {
 	IB_POLL_DIRECT,		   /* caller context, no hw completions */
 	IB_POLL_SOFTIRQ,	   /* poll from softirq context */
 	IB_POLL_WORKQUEUE,	   /* poll from workqueue */
+	IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */
 };
 
 struct ib_cq {
@@ -1589,6 +1591,7 @@ struct ib_cq {
 		struct irq_poll		iop;
 		struct work_struct	work;
 	};
+	struct workqueue_struct *comp_wq;
 	/*
 	 * Implementation details of the RDMA core, don't use in drivers:
 	 */