xprtrdma: Move send_wr to struct rpcrdma_req

Clean up: Most of the fields in each send_wr do not vary. There is
no need to initialize them before each ib_post_send(). This removes
a large-ish data structure from the stack.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

net/sunrpc/xprtrdma/backchannel.c

@@ -241,7 +241,8 @@ int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst)
 	req->rl_send_iov[1].length = rpclen;
 	req->rl_send_iov[1].lkey = rdmab_lkey(req->rl_sendbuf);
 
-	req->rl_niovs = 2;
+	req->rl_send_wr.num_sge = 2;
+
 	return 0;
 
 out_map:

net/sunrpc/xprtrdma/rpc_rdma.c

@@ -687,7 +687,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	req->rl_send_iov[0].length = hdrlen;
 	req->rl_send_iov[0].lkey = rdmab_lkey(req->rl_rdmabuf);
 
-	req->rl_niovs = 1;
+	req->rl_send_wr.num_sge = 1;
 	if (rtype == rpcrdma_areadch)
 		return 0;
 
@@ -697,7 +697,8 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	req->rl_send_iov[1].length = rpclen;
 	req->rl_send_iov[1].lkey = rdmab_lkey(req->rl_sendbuf);
 
-	req->rl_niovs = 2;
+	req->rl_send_wr.num_sge = 2;
+
 	return 0;
 
 out_overflow:

net/sunrpc/xprtrdma/verbs.c

@@ -849,6 +849,10 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt)
 	req->rl_cqe.done = rpcrdma_wc_send;
 	req->rl_buffer = &r_xprt->rx_buf;
 	INIT_LIST_HEAD(&req->rl_registered);
+	req->rl_send_wr.next = NULL;
+	req->rl_send_wr.wr_cqe = &req->rl_cqe;
+	req->rl_send_wr.sg_list = req->rl_send_iov;
+	req->rl_send_wr.opcode = IB_WR_SEND;
 	return req;
 }
 
@@ -1128,7 +1132,7 @@ rpcrdma_buffer_put(struct rpcrdma_req *req)
 	struct rpcrdma_buffer *buffers = req->rl_buffer;
 	struct rpcrdma_rep *rep = req->rl_reply;
 
-	req->rl_niovs = 0;
+	req->rl_send_wr.num_sge = 0;
 	req->rl_reply = NULL;
 
 	spin_lock(&buffers->rb_lock);
@@ -1259,38 +1263,32 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 		struct rpcrdma_req *req)
 {
 	struct ib_device *device = ia->ri_device;
-	struct ib_send_wr send_wr, *send_wr_fail;
-	struct rpcrdma_rep *rep = req->rl_reply;
-	struct ib_sge *iov = req->rl_send_iov;
+	struct ib_send_wr *send_wr = &req->rl_send_wr;
+	struct ib_send_wr *send_wr_fail;
+	struct ib_sge *sge = req->rl_send_iov;
 	int i, rc;
 
-	if (rep) {
-		rc = rpcrdma_ep_post_recv(ia, rep);
+	if (req->rl_reply) {
+		rc = rpcrdma_ep_post_recv(ia, req->rl_reply);
 		if (rc)
 			return rc;
 		req->rl_reply = NULL;
 	}
 
-	send_wr.next = NULL;
-	send_wr.wr_cqe = &req->rl_cqe;
-	send_wr.sg_list = iov;
-	send_wr.num_sge = req->rl_niovs;
-	send_wr.opcode = IB_WR_SEND;
-
-	for (i = 0; i < send_wr.num_sge; i++)
-		ib_dma_sync_single_for_device(device, iov[i].addr,
-					      iov[i].length, DMA_TO_DEVICE);
+	for (i = 0; i < send_wr->num_sge; i++)
+		ib_dma_sync_single_for_device(device, sge[i].addr,
+					      sge[i].length, DMA_TO_DEVICE);
 	dprintk("RPC:       %s: posting %d s/g entries\n",
-		__func__, send_wr.num_sge);
+		__func__, send_wr->num_sge);
 
 	if (DECR_CQCOUNT(ep) > 0)
-		send_wr.send_flags = 0;
+		send_wr->send_flags = 0;
 	else { /* Provider must take a send completion every now and then */
 		INIT_CQCOUNT(ep);
-		send_wr.send_flags = IB_SEND_SIGNALED;
+		send_wr->send_flags = IB_SEND_SIGNALED;
 	}
 
-	rc = ib_post_send(ia->ri_id->qp, &send_wr, &send_wr_fail);
+	rc = ib_post_send(ia->ri_id->qp, send_wr, &send_wr_fail);
 	if (rc)
 		goto out_postsend_err;
 	return 0;

net/sunrpc/xprtrdma/xprt_rdma.h

@@ -284,10 +284,10 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
 struct rpcrdma_buffer;
 struct rpcrdma_req {
 	struct list_head	rl_free;
-	unsigned int		rl_niovs;
 	unsigned int		rl_connect_cookie;
 	struct rpcrdma_buffer	*rl_buffer;
-	struct rpcrdma_rep	*rl_reply;/* holder for reply buffer */
+	struct rpcrdma_rep	*rl_reply;
+	struct ib_send_wr	rl_send_wr;
 	struct ib_sge		rl_send_iov[RPCRDMA_MAX_IOVS];
 	struct rpcrdma_regbuf	*rl_rdmabuf;	/* xprt header */
 	struct rpcrdma_regbuf	*rl_sendbuf;	/* rq_snd_buf */