1 files changed, 52 insertions, 3 deletions

diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 7c599878ccf7..4f25b2400694 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -7,6 +7,8 @@
 #include <linux/slab.h>
 #include <rdma/ib_verbs.h>
 
+#include <trace/events/rdma_core.h>
+
 /* # of WCs to poll for with a single call to ib_poll_cq */
 #define IB_POLL_BATCH			16
 #define IB_POLL_BATCH_DIRECT		8
@@ -41,6 +43,7 @@ static void ib_cq_rdma_dim_work(struct work_struct *w)
 
 	dim->state = DIM_START_MEASURE;
 
+	trace_cq_modify(cq, comps, usec);
 	cq->device->ops.modify_cq(cq, comps, usec);
 }
 
@@ -65,18 +68,29 @@ static void rdma_dim_init(struct ib_cq *cq)
 	INIT_WORK(&dim->work, ib_cq_rdma_dim_work);
 }
 
+static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc)
+{
+	int rc;
+
+	rc = ib_poll_cq(cq, num_entries, wc);
+	trace_cq_poll(cq, num_entries, rc);
+	return rc;
+}
+
 static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs,
 			   int batch)
 {
 	int i, n, completed = 0;
 
+	trace_cq_process(cq);
+
 	/*
 	 * budget might be (-1) if the caller does not
 	 * want to bound this call, thus we need unsigned
 	 * minimum here.
 	 */
-	while ((n = ib_poll_cq(cq, min_t(u32, batch,
-					 budget - completed), wcs)) > 0) {
+	while ((n = __poll_cq(cq, min_t(u32, batch,
+					budget - completed), wcs)) > 0) {
 		for (i = 0; i < n; i++) {
 			struct ib_wc *wc = &wcs[i];
 
@@ -131,8 +145,10 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 	completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH);
 	if (completed < budget) {
 		irq_poll_complete(&cq->iop);
-		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
+		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) {
+			trace_cq_reschedule(cq);
 			irq_poll_sched(&cq->iop);
+		}
 	}
 
 	if (dim)
@@ -143,6 +159,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 
 static void ib_cq_completion_softirq(struct ib_cq *cq, void *private)
 {
+	trace_cq_schedule(cq);
 	irq_poll_sched(&cq->iop);
 }
 
@@ -162,6 +179,7 @@ static void ib_cq_poll_work(struct work_struct *work)
 
 static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 {
+	trace_cq_schedule(cq);
 	queue_work(cq->comp_wq, &cq->work);
 }
 
@@ -239,6 +257,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
 		goto out_destroy_cq;
 	}
 
+	trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx);
 	return cq;
 
 out_destroy_cq:
@@ -248,11 +267,40 @@ out_free_wc:
 	kfree(cq->wc);
 out_free_cq:
 	kfree(cq);
+	trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(__ib_alloc_cq_user);
 
 /**
+ * __ib_alloc_cq_any - allocate a completion queue
+ * @dev:		device to allocate the CQ for
+ * @private:		driver private data, accessible from cq->cq_context
+ * @nr_cqe:		number of CQEs to allocate
+ * @poll_ctx:		context to poll the CQ from
+ * @caller:		module owner name
+ *
+ * Attempt to spread ULP Completion Queues over each device's interrupt
+ * vectors. A simple best-effort mechanism is used.
+ */
+struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
+				int nr_cqe, enum ib_poll_context poll_ctx,
+				const char *caller)
+{
+	static atomic_t counter;
+	int comp_vector = 0;
+
+	if (dev->num_comp_vectors > 1)
+		comp_vector =
+			atomic_inc_return(&counter) %
+			min_t(int, dev->num_comp_vectors, num_online_cpus());
+
+	return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx,
+				  caller, NULL);
+}
+EXPORT_SYMBOL(__ib_alloc_cq_any);
+
+/**
  * ib_free_cq_user - free a completion queue
  * @cq:		completion queue to free.
  * @udata:	User data or NULL for kernel object
@@ -276,6 +324,7 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
 		WARN_ON_ONCE(1);
 	}
 
+	trace_cq_free(cq);
 	rdma_restrack_del(&cq->res);
 	cq->device->ops.destroy_cq(cq, udata);
 	if (cq->dim)