rdma: Enable ib_alloc_cq to spread work over a device's comp_vectors

Send and Receive completion is handled on a single CPU selected at
the time each Completion Queue is allocated. Typically this is when
an initiator instantiates an RDMA transport, or when a target
accepts an RDMA connection.

Some ULPs cannot open a connection per CPU to spread completion
workload across available CPUs and MSI vectors. For such ULPs,
provide an API that allows the RDMA core to select a completion
vector based on the device's complement of available comp_vecs.

ULPs that invoke ib_alloc_cq() with only comp_vector 0 are converted
to use the new API so that their completion workloads interfere less
with each other.

Suggested-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Cc: <linux-cifs@vger.kernel.org>
Cc: <v9fs-developer@lists.sourceforge.net>
Link: https://lore.kernel.org/r/20190729171923.13428.52555.stgit@manet.1015granger.net
Signed-off-by: Doug Ledford <dledford@redhat.com>

3 files changed, 13 insertions, 14 deletions

diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index bac8dad5dd69..b21c3c209815 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -685,9 +685,9 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
 		goto error;
 
 	/* Create the Completion Queue */
-	rdma->cq = ib_alloc_cq(rdma->cm_id->device, client,
-			opts.sq_depth + opts.rq_depth + 1,
-			0, IB_POLL_SOFTIRQ);
+	rdma->cq = ib_alloc_cq_any(rdma->cm_id->device, client,
+				   opts.sq_depth + opts.rq_depth + 1,
+				   IB_POLL_SOFTIRQ);
 	if (IS_ERR(rdma->cq))
 		goto error;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 3fe665152d95..4d3db6ee7f09 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -454,14 +454,14 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 		dprintk("svcrdma: error creating PD for connect request\n");
 		goto errout;
 	}
-	newxprt->sc_sq_cq = ib_alloc_cq(dev, newxprt, newxprt->sc_sq_depth,
-					0, IB_POLL_WORKQUEUE);
+	newxprt->sc_sq_cq = ib_alloc_cq_any(dev, newxprt, newxprt->sc_sq_depth,
+					    IB_POLL_WORKQUEUE);
 	if (IS_ERR(newxprt->sc_sq_cq)) {
 		dprintk("svcrdma: error creating SQ CQ for connect request\n");
 		goto errout;
 	}
-	newxprt->sc_rq_cq = ib_alloc_cq(dev, newxprt, rq_depth,
-					0, IB_POLL_WORKQUEUE);
+	newxprt->sc_rq_cq =
+		ib_alloc_cq_any(dev, newxprt, rq_depth, IB_POLL_WORKQUEUE);
 	if (IS_ERR(newxprt->sc_rq_cq)) {
 		dprintk("svcrdma: error creating RQ CQ for connect request\n");
 		goto errout;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 805b1f35e1ca..b10aa16557f0 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -521,18 +521,17 @@ int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 	init_waitqueue_head(&ep->rep_connect_wait);
 	ep->rep_receive_count = 0;
 
-	sendcq = ib_alloc_cq(ia->ri_id->device, NULL,
-			     ep->rep_attr.cap.max_send_wr + 1,
-			     ia->ri_id->device->num_comp_vectors > 1 ? 1 : 0,
-			     IB_POLL_WORKQUEUE);
+	sendcq = ib_alloc_cq_any(ia->ri_id->device, NULL,
+				 ep->rep_attr.cap.max_send_wr + 1,
+				 IB_POLL_WORKQUEUE);
 	if (IS_ERR(sendcq)) {
 		rc = PTR_ERR(sendcq);
 		goto out1;
 	}
 
-	recvcq = ib_alloc_cq(ia->ri_id->device, NULL,
-			     ep->rep_attr.cap.max_recv_wr + 1,
-			     0, IB_POLL_WORKQUEUE);
+	recvcq = ib_alloc_cq_any(ia->ri_id->device, NULL,
+				 ep->rep_attr.cap.max_recv_wr + 1,
+				 IB_POLL_WORKQUEUE);
 	if (IS_ERR(recvcq)) {
 		rc = PTR_ERR(recvcq);
 		goto out2;