xprtrdma: Trace unmap_sync calls

->buf_free is called nearly once per RPC. Only rarely does
xprt_rdma_free() have to do anything, thus tracing every one of
these calls seems unnecessary. Instead, just throw a trace event
when that one occasional RPC still has MRs that need to be
released.

xprt_rdma_free() is further micro-optimized to reduce the amount of
work done in the common case.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

include/trace/events/rpcrdma.h

@@ -1167,6 +1167,28 @@ TRACE_EVENT(xprtrdma_decode_seg,
 	)
 );
 
+TRACE_EVENT(xprtrdma_mrs_zap,
+	TP_PROTO(
+		const struct rpc_task *task
+	),
+
+	TP_ARGS(task),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client->cl_clid;
+	),
+
+	TP_printk("task:%u@%u",
+		__entry->task_id, __entry->client_id
+	)
+);
+
 /**
  ** Callback events
  **/

net/sunrpc/xprtrdma/transport.c

@@ -599,11 +599,12 @@ static void
 xprt_rdma_free(struct rpc_task *task)
 {
 	struct rpc_rqst *rqst = task->tk_rqstp;
-	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 
-	if (!list_empty(&req->rl_registered))
-		frwr_unmap_sync(r_xprt, req);
+	if (unlikely(!list_empty(&req->rl_registered))) {
+		trace_xprtrdma_mrs_zap(task);
+		frwr_unmap_sync(rpcx_to_rdmax(rqst->rq_xprt), req);
+	}
 
 	/* XXX: If the RPC is completing because of a signal and
 	 * not because a reply was received, we ought to ensure