From a2268cfbf599e7f55d4ee68193f08b4f44535fac Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:34:32 -0400
Subject: xprtrdma: Add proper SPDX tags for NetApp-contributed source

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/module.c    | 1 +
 net/sunrpc/xprtrdma/rpc_rdma.c  | 1 +
 net/sunrpc/xprtrdma/transport.c | 1 +
 net/sunrpc/xprtrdma/verbs.c     | 1 +
 net/sunrpc/xprtrdma/xprt_rdma.h | 1 +
 5 files changed, 5 insertions(+)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c
index a762d192372b..f338065121f2 100644
--- a/net/sunrpc/xprtrdma/module.c
+++ b/net/sunrpc/xprtrdma/module.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (c) 2015, 2017 Oracle.  All rights reserved.
  */
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index e8adad33d0bb..8f89e3faae8e 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (c) 2014-2017 Oracle.  All rights reserved.
  * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index cc1aad325496..4717578b4b81 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (c) 2014-2017 Oracle.  All rights reserved.
  * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index fe5eaca2d197..b2c6f525b020 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (c) 2014-2017 Oracle.  All rights reserved.
  * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 3d3b423fa9c1..3490a87bc69a 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
  * Copyright (c) 2014-2017 Oracle.  All rights reserved.
  * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
-- 
cgit v1.2.3


From 52d28fe4f61350baf7e84b3f3f3e34f0fc077ec1 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:34:37 -0400
Subject: xprtrdma: Try to fail quickly if proto=rdma

rdma_resolve_addr(3) says:

> This call is used to map a given destination IP address to a
> usable RDMA address. The IP to RDMA address mapping is done
> using the local routing tables, or via ARP.

If this can't be done, there's no local device that can be used
to establish an RDMA-capable network path to the remote. In this
case, the RDMA CM very quickly posts an RDMA_CM_EVENT_ADDR_ERROR
upcall.

Currently rpcrdma_conn_upcall() converts RDMA_CM_EVENT_ADDR_ERROR
to EHOSTUNREACH. mount.nfs seems to want to retry EHOSTUNREACH
forever, thinking that this is a temporary situation. This makes
mount.nfs appear to hang if I try to mount with proto=rdma through,
say, a conventional Ethernet device.

If the admin has specified proto=rdma along with a server IP address
that requires a network path that does not support RDMA, instead
let's fail with a permanent error. -EPROTONOSUPPORT is returned when
NFSv4 or one of its minor versions is not supported.

-EPROTO is not (currently) retried by mount.nfs.

There are potentially other similar cases where -EPROTO is an
appropriate return code.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Olga Kornievskaia <kolga@netapp.com>
Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index b2c6f525b020..4ee9704ffe19 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -232,7 +232,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
 		complete(&ia->ri_done);
 		break;
 	case RDMA_CM_EVENT_ADDR_ERROR:
-		ia->ri_async_rc = -EHOSTUNREACH;
+		ia->ri_async_rc = -EPROTO;
 		complete(&ia->ri_done);
 		break;
 	case RDMA_CM_EVENT_ROUTE_ERROR:
@@ -263,7 +263,7 @@ rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
 		connstate = -ENOTCONN;
 		goto connected;
 	case RDMA_CM_EVENT_UNREACHABLE:
-		connstate = -ENETDOWN;
+		connstate = -ENETUNREACH;
 		goto connected;
 	case RDMA_CM_EVENT_REJECTED:
 		dprintk("rpcrdma: connection to %s:%s rejected: %s\n",
-- 
cgit v1.2.3


From 107c4beb9bedd07d6e22f7010333dba3dc988292 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:34:42 -0400
Subject: xprtrdma: Create transport's CM ID in the correct network namespace

Set up RPC/RDMA transport in mount.nfs's network namespace. This
passes the correct namespace information to the RDMA core, similar
to how RPC sockets are created (see xs_create_sock).

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 4ee9704ffe19..07529ef8e33e 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -306,8 +306,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia)
 	init_completion(&ia->ri_done);
 	init_completion(&ia->ri_remove_done);
 
-	id = rdma_create_id(&init_net, rpcrdma_conn_upcall, xprt, RDMA_PS_TCP,
-			    IB_QPT_RC);
+	id = rdma_create_id(xprt->rx_xprt.xprt_net, rpcrdma_conn_upcall,
+			    xprt, RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(id)) {
 		rc = PTR_ERR(id);
 		dprintk("RPC:       %s: rdma_create_id() failed %i\n",
-- 
cgit v1.2.3


From 914fcad9873cbd46e3a4c3c31551b98b15a49079 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:34:48 -0400
Subject: xprtrdma: Fix max_send_wr computation

For FRWR, the computation of max_send_wr is split between
frwr_op_open and rpcrdma_ep_create, which makes it difficult to tell
that the max_send_wr result is currently incorrect if frwr_op_open
has to reduce the credit limit to accommodate a small max_qp_wr.
This is a problem now that extra WRs are needed for backchannel
operations and a drain CQE.

So, refactor the computation so that it is all done in ->ro_open,
and fix the FRWR version of this computation so that it
accommodates HCAs with small max_qp_wr correctly.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/fmr_ops.c  | 22 ++++++++++++++++++++++
 net/sunrpc/xprtrdma/frwr_ops.c | 30 ++++++++++++++++++++++++++----
 net/sunrpc/xprtrdma/verbs.c    | 24 ++++--------------------
 3 files changed, 52 insertions(+), 24 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 5cc68a824f45..592d1e8e27c3 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -159,10 +159,32 @@ out_release:
 	fmr_op_release_mr(mr);
 }
 
+/* On success, sets:
+ *	ep->rep_attr.cap.max_send_wr
+ *	ep->rep_attr.cap.max_recv_wr
+ *	cdata->max_requests
+ *	ia->ri_max_segs
+ */
 static int
 fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 	    struct rpcrdma_create_data_internal *cdata)
 {
+	int max_qp_wr;
+
+	max_qp_wr = ia->ri_device->attrs.max_qp_wr;
+	max_qp_wr -= RPCRDMA_BACKWARD_WRS;
+	max_qp_wr -= 1;
+	if (max_qp_wr < RPCRDMA_MIN_SLOT_TABLE)
+		return -ENOMEM;
+	if (cdata->max_requests > max_qp_wr)
+		cdata->max_requests = max_qp_wr;
+	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
+	ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_send_wr += 1; /* for ib_drain_sq */
+	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
+	ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_recv_wr += 1; /* for ib_drain_rq */
+
 	ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS /
 				RPCRDMA_MAX_FMR_SGES);
 	return 0;
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index c5743a0960be..0f2e108d387e 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -205,12 +205,22 @@ out_release:
 	frwr_op_release_mr(mr);
 }
 
+/* On success, sets:
+ *	ep->rep_attr.cap.max_send_wr
+ *	ep->rep_attr.cap.max_recv_wr
+ *	cdata->max_requests
+ *	ia->ri_max_segs
+ *
+ * And these FRWR-related fields:
+ *	ia->ri_max_frwr_depth
+ *	ia->ri_mrtype
+ */
 static int
 frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 	     struct rpcrdma_create_data_internal *cdata)
 {
 	struct ib_device_attr *attrs = &ia->ri_device->attrs;
-	int depth, delta;
+	int max_qp_wr, depth, delta;
 
 	ia->ri_mrtype = IB_MR_TYPE_MEM_REG;
 	if (attrs->device_cap_flags & IB_DEVICE_SG_GAPS_REG)
@@ -244,14 +254,26 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 		} while (delta > 0);
 	}
 
-	ep->rep_attr.cap.max_send_wr *= depth;
-	if (ep->rep_attr.cap.max_send_wr > attrs->max_qp_wr) {
-		cdata->max_requests = attrs->max_qp_wr / depth;
+	max_qp_wr = ia->ri_device->attrs.max_qp_wr;
+	max_qp_wr -= RPCRDMA_BACKWARD_WRS;
+	max_qp_wr -= 1;
+	if (max_qp_wr < RPCRDMA_MIN_SLOT_TABLE)
+		return -ENOMEM;
+	if (cdata->max_requests > max_qp_wr)
+		cdata->max_requests = max_qp_wr;
+	ep->rep_attr.cap.max_send_wr = cdata->max_requests * depth;
+	if (ep->rep_attr.cap.max_send_wr > max_qp_wr) {
+		cdata->max_requests = max_qp_wr / depth;
 		if (!cdata->max_requests)
 			return -EINVAL;
 		ep->rep_attr.cap.max_send_wr = cdata->max_requests *
 					       depth;
 	}
+	ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_send_wr += 1; /* for ib_drain_sq */
+	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
+	ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
+	ep->rep_attr.cap.max_recv_wr += 1; /* for ib_drain_rq */
 
 	ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS /
 				ia->ri_max_frwr_depth);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 07529ef8e33e..62baddefced3 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -501,8 +501,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 		  struct rpcrdma_create_data_internal *cdata)
 {
 	struct rpcrdma_connect_private *pmsg = &ep->rep_cm_private;
-	unsigned int max_qp_wr, max_sge;
 	struct ib_cq *sendcq, *recvcq;
+	unsigned int max_sge;
 	int rc;
 
 	max_sge = min_t(unsigned int, ia->ri_device->attrs.max_sge,
@@ -513,29 +513,13 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	}
 	ia->ri_max_send_sges = max_sge;
 
-	if (ia->ri_device->attrs.max_qp_wr <= RPCRDMA_BACKWARD_WRS) {
-		dprintk("RPC:       %s: insufficient wqe's available\n",
-			__func__);
-		return -ENOMEM;
-	}
-	max_qp_wr = ia->ri_device->attrs.max_qp_wr - RPCRDMA_BACKWARD_WRS - 1;
-
-	/* check provider's send/recv wr limits */
-	if (cdata->max_requests > max_qp_wr)
-		cdata->max_requests = max_qp_wr;
+	rc = ia->ri_ops->ro_open(ia, ep, cdata);
+	if (rc)
+		return rc;
 
 	ep->rep_attr.event_handler = rpcrdma_qp_async_error_upcall;
 	ep->rep_attr.qp_context = ep;
 	ep->rep_attr.srq = NULL;
-	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
-	ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS;
-	ep->rep_attr.cap.max_send_wr += 1;	/* drain cqe */
-	rc = ia->ri_ops->ro_open(ia, ep, cdata);
-	if (rc)
-		return rc;
-	ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
-	ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
-	ep->rep_attr.cap.max_recv_wr += 1;	/* drain cqe */
 	ep->rep_attr.cap.max_send_sge = max_sge;
 	ep->rep_attr.cap.max_recv_sge = 1;
 	ep->rep_attr.cap.max_inline_data = 0;
-- 
cgit v1.2.3


From a9cde23ab7cdf5e4e93432dffd0e734267f2b745 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:34:59 -0400
Subject: SUNRPC: Add a ->free_slot transport callout

Refactor: xprtrdma needs to have better control over when RPCs are
awoken from the backlog queue, so replace xprt_free_slot with a
transport op callout.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 1 +
 net/sunrpc/xprtrdma/transport.c            | 1 +
 2 files changed, 2 insertions(+)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index a73632ca9048..1035516d54e2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -273,6 +273,7 @@ static const struct rpc_xprt_ops xprt_rdma_bc_procs = {
 	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong,
 	.alloc_slot		= xprt_alloc_slot,
+	.free_slot		= xprt_free_slot,
 	.release_request	= xprt_release_rqst_cong,
 	.buf_alloc		= xprt_rdma_bc_allocate,
 	.buf_free		= xprt_rdma_bc_free,
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 4717578b4b81..cf5e866ee969 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -781,6 +781,7 @@ static const struct rpc_xprt_ops xprt_rdma_procs = {
 	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong, /* sunrpc/xprt.c */
 	.alloc_slot		= xprt_alloc_slot,
+	.free_slot		= xprt_free_slot,
 	.release_request	= xprt_release_rqst_cong,       /* ditto */
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def, /* ditto */
 	.timer			= xprt_rdma_timer,
-- 
cgit v1.2.3


From 48be539dd44a3a010a6a330d09610d60ad42758a Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:04 -0400
Subject: xprtrdma: Introduce ->alloc_slot call-out for xprtrdma

rpcrdma_buffer_get acquires an rpcrdma_req and rep for each RPC.
Currently this is done in the call_allocate action, and sometimes it
can fail if there are many outstanding RPCs.

When call_allocate fails, the RPC task is put on the delayq. It is
awoken a few milliseconds later, but there's no guarantee it will
get a buffer at that time. The RPC task can be repeatedly put back
to sleep or even starved.

The call_allocate action should rarely fail. The delayq mechanism is
not meant to deal with transport congestion.

In the current sunrpc stack, there is a friendlier way to deal with
this situation. These objects are actually tantamount to an RPC
slot (rpc_rqst) and there is a separate FSM action, distinct from
call_allocate, for allocating slot resources. This is the
call_reserve action.

When allocation fails during this action, the RPC is placed on the
transport's backlog queue. The backlog mechanism provides a stronger
guarantee that when the RPC is awoken, a buffer will be available
for it; and backlogged RPCs are awoken one-at-a-time.

To make slot resource allocation occur in the call_reserve action,
create special ->alloc_slot and ->free_slot call-outs for xprtrdma.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/transport.c | 52 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index cf5e866ee969..8f9338e98c4f 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -538,6 +538,54 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 	}
 }
 
+/**
+ * xprt_rdma_alloc_slot - allocate an rpc_rqst
+ * @xprt: controlling RPC transport
+ * @task: RPC task requesting a fresh rpc_rqst
+ *
+ * tk_status values:
+ *	%0 if task->tk_rqstp points to a fresh rpc_rqst
+ *	%-EAGAIN if no rpc_rqst is available; queued on backlog
+ */
+static void
+xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
+{
+	struct rpc_rqst *rqst;
+
+	spin_lock(&xprt->reserve_lock);
+	if (list_empty(&xprt->free))
+		goto out_sleep;
+	rqst = list_first_entry(&xprt->free, struct rpc_rqst, rq_list);
+	list_del(&rqst->rq_list);
+	spin_unlock(&xprt->reserve_lock);
+
+	task->tk_rqstp = rqst;
+	task->tk_status = 0;
+	return;
+
+out_sleep:
+	rpc_sleep_on(&xprt->backlog, task, NULL);
+	spin_unlock(&xprt->reserve_lock);
+	task->tk_status = -EAGAIN;
+}
+
+/**
+ * xprt_rdma_free_slot - release an rpc_rqst
+ * @xprt: controlling RPC transport
+ * @rqst: rpc_rqst to release
+ *
+ */
+static void
+xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst)
+{
+	memset(rqst, 0, sizeof(*rqst));
+
+	spin_lock(&xprt->reserve_lock);
+	list_add(&rqst->rq_list, &xprt->free);
+	rpc_wake_up_next(&xprt->backlog);
+	spin_unlock(&xprt->reserve_lock);
+}
+
 static bool
 rpcrdma_get_sendbuf(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		    size_t size, gfp_t flags)
@@ -780,8 +828,8 @@ xprt_rdma_disable_swap(struct rpc_xprt *xprt)
 static const struct rpc_xprt_ops xprt_rdma_procs = {
 	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong, /* sunrpc/xprt.c */
-	.alloc_slot		= xprt_alloc_slot,
-	.free_slot		= xprt_free_slot,
+	.alloc_slot		= xprt_rdma_alloc_slot,
+	.free_slot		= xprt_rdma_free_slot,
 	.release_request	= xprt_release_rqst_cong,       /* ditto */
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def, /* ditto */
 	.timer			= xprt_rdma_timer,
-- 
cgit v1.2.3


From edb41e61a54ee75fae31302775e0301fdcb0caaa Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:09 -0400
Subject: xprtrdma: Make rpc_rqst part of rpcrdma_req

This simplifies allocation of the generic RPC slot and xprtrdma
specific per-RPC resources.

It also makes xprtrdma more like the socket-based transports:
->buf_alloc and ->buf_free are now responsible only for send and
receive buffers.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/backchannel.c | 77 ++++++++++++++++++---------------------
 net/sunrpc/xprtrdma/transport.c   | 35 +++++-------------
 net/sunrpc/xprtrdma/xprt_rdma.h   |  9 +----
 3 files changed, 46 insertions(+), 75 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 47ebac949769..4034788c9856 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -29,29 +29,41 @@ static void rpcrdma_bc_free_rqst(struct rpcrdma_xprt *r_xprt,
 	spin_unlock(&buf->rb_reqslock);
 
 	rpcrdma_destroy_req(req);
-
-	kfree(rqst);
 }
 
-static int rpcrdma_bc_setup_rqst(struct rpcrdma_xprt *r_xprt,
-				 struct rpc_rqst *rqst)
+static int rpcrdma_bc_setup_reqs(struct rpcrdma_xprt *r_xprt,
+				 unsigned int count)
 {
-	struct rpcrdma_regbuf *rb;
-	struct rpcrdma_req *req;
-	size_t size;
+	struct rpc_xprt *xprt = &r_xprt->rx_xprt;
+	struct rpc_rqst *rqst;
+	unsigned int i;
+
+	for (i = 0; i < (count << 1); i++) {
+		struct rpcrdma_regbuf *rb;
+		struct rpcrdma_req *req;
+		size_t size;
+
+		req = rpcrdma_create_req(r_xprt);
+		if (IS_ERR(req))
+			return PTR_ERR(req);
+		rqst = &req->rl_slot;
+
+		rqst->rq_xprt = xprt;
+		INIT_LIST_HEAD(&rqst->rq_list);
+		INIT_LIST_HEAD(&rqst->rq_bc_list);
+		__set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state);
+		spin_lock_bh(&xprt->bc_pa_lock);
+		list_add(&rqst->rq_bc_pa_list, &xprt->bc_pa_list);
+		spin_unlock_bh(&xprt->bc_pa_lock);
 
-	req = rpcrdma_create_req(r_xprt);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-
-	size = r_xprt->rx_data.inline_rsize;
-	rb = rpcrdma_alloc_regbuf(size, DMA_TO_DEVICE, GFP_KERNEL);
-	if (IS_ERR(rb))
-		goto out_fail;
-	req->rl_sendbuf = rb;
-	xdr_buf_init(&rqst->rq_snd_buf, rb->rg_base,
-		     min_t(size_t, size, PAGE_SIZE));
-	rpcrdma_set_xprtdata(rqst, req);
+		size = r_xprt->rx_data.inline_rsize;
+		rb = rpcrdma_alloc_regbuf(size, DMA_TO_DEVICE, GFP_KERNEL);
+		if (IS_ERR(rb))
+			goto out_fail;
+		req->rl_sendbuf = rb;
+		xdr_buf_init(&rqst->rq_snd_buf, rb->rg_base,
+			     min_t(size_t, size, PAGE_SIZE));
+	}
 	return 0;
 
 out_fail:
@@ -86,9 +98,6 @@ static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt,
 int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs)
 {
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	struct rpcrdma_buffer *buffer = &r_xprt->rx_buf;
-	struct rpc_rqst *rqst;
-	unsigned int i;
 	int rc;
 
 	/* The backchannel reply path returns each rpc_rqst to the
@@ -103,25 +112,9 @@ int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs)
 	if (reqs > RPCRDMA_BACKWARD_WRS >> 1)
 		goto out_err;
 
-	for (i = 0; i < (reqs << 1); i++) {
-		rqst = kzalloc(sizeof(*rqst), GFP_KERNEL);
-		if (!rqst)
-			goto out_free;
-
-		dprintk("RPC:       %s: new rqst %p\n", __func__, rqst);
-
-		rqst->rq_xprt = &r_xprt->rx_xprt;
-		INIT_LIST_HEAD(&rqst->rq_list);
-		INIT_LIST_HEAD(&rqst->rq_bc_list);
-		__set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state);
-
-		if (rpcrdma_bc_setup_rqst(r_xprt, rqst))
-			goto out_free;
-
-		spin_lock_bh(&xprt->bc_pa_lock);
-		list_add(&rqst->rq_bc_pa_list, &xprt->bc_pa_list);
-		spin_unlock_bh(&xprt->bc_pa_lock);
-	}
+	rc = rpcrdma_bc_setup_reqs(r_xprt, reqs);
+	if (rc)
+		goto out_free;
 
 	rc = rpcrdma_bc_setup_reps(r_xprt, reqs);
 	if (rc)
@@ -131,7 +124,7 @@ int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs)
 	if (rc)
 		goto out_free;
 
-	buffer->rb_bc_srv_max_requests = reqs;
+	r_xprt->rx_buf.rb_bc_srv_max_requests = reqs;
 	request_module("svcrdma");
 	trace_xprtrdma_cb_setup(r_xprt, reqs);
 	return 0;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 8f9338e98c4f..79885aa39c24 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -331,9 +331,7 @@ xprt_setup_rdma(struct xprt_create *args)
 		return ERR_PTR(-EBADF);
 	}
 
-	xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt),
-			xprt_rdma_slot_table_entries,
-			xprt_rdma_slot_table_entries);
+	xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt), 0, 0);
 	if (xprt == NULL) {
 		dprintk("RPC:       %s: couldn't allocate rpcrdma_xprt\n",
 			__func__);
@@ -365,7 +363,7 @@ xprt_setup_rdma(struct xprt_create *args)
 		xprt_set_bound(xprt);
 	xprt_rdma_format_addresses(xprt, sap);
 
-	cdata.max_requests = xprt->max_reqs;
+	cdata.max_requests = xprt_rdma_slot_table_entries;
 
 	cdata.rsize = RPCRDMA_MAX_SEGS * PAGE_SIZE; /* RDMA write max */
 	cdata.wsize = RPCRDMA_MAX_SEGS * PAGE_SIZE; /* RDMA read max */
@@ -550,22 +548,18 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 static void
 xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
 {
-	struct rpc_rqst *rqst;
+	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	struct rpcrdma_req *req;
 
-	spin_lock(&xprt->reserve_lock);
-	if (list_empty(&xprt->free))
+	req = rpcrdma_buffer_get(&r_xprt->rx_buf);
+	if (!req)
 		goto out_sleep;
-	rqst = list_first_entry(&xprt->free, struct rpc_rqst, rq_list);
-	list_del(&rqst->rq_list);
-	spin_unlock(&xprt->reserve_lock);
-
-	task->tk_rqstp = rqst;
+	task->tk_rqstp = &req->rl_slot;
 	task->tk_status = 0;
 	return;
 
 out_sleep:
 	rpc_sleep_on(&xprt->backlog, task, NULL);
-	spin_unlock(&xprt->reserve_lock);
 	task->tk_status = -EAGAIN;
 }
 
@@ -579,11 +573,8 @@ static void
 xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst)
 {
 	memset(rqst, 0, sizeof(*rqst));
-
-	spin_lock(&xprt->reserve_lock);
-	list_add(&rqst->rq_list, &xprt->free);
+	rpcrdma_buffer_put(rpcr_to_rdmar(rqst));
 	rpc_wake_up_next(&xprt->backlog);
-	spin_unlock(&xprt->reserve_lock);
 }
 
 static bool
@@ -656,13 +647,9 @@ xprt_rdma_allocate(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;
+	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	gfp_t flags;
 
-	req = rpcrdma_buffer_get(&r_xprt->rx_buf);
-	if (req == NULL)
-		goto out_get;
-
 	flags = RPCRDMA_DEF_GFP;
 	if (RPC_IS_SWAPPER(task))
 		flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN;
@@ -672,15 +659,12 @@ xprt_rdma_allocate(struct rpc_task *task)
 	if (!rpcrdma_get_recvbuf(r_xprt, req, rqst->rq_rcvsize, flags))
 		goto out_fail;
 
-	rpcrdma_set_xprtdata(rqst, req);
 	rqst->rq_buffer = req->rl_sendbuf->rg_base;
 	rqst->rq_rbuffer = req->rl_recvbuf->rg_base;
 	trace_xprtrdma_allocate(task, req);
 	return 0;
 
 out_fail:
-	rpcrdma_buffer_put(req);
-out_get:
 	trace_xprtrdma_allocate(task, NULL);
 	return -ENOMEM;
 }
@@ -701,7 +685,6 @@ xprt_rdma_free(struct rpc_task *task)
 	if (test_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags))
 		rpcrdma_release_rqst(r_xprt, req);
 	trace_xprtrdma_rpc_done(task, req);
-	rpcrdma_buffer_put(req);
 }
 
 /**
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 3490a87bc69a..1d7bb6e5db18 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -335,6 +335,7 @@ enum {
 struct rpcrdma_buffer;
 struct rpcrdma_req {
 	struct list_head	rl_list;
+	struct rpc_rqst		rl_slot;
 	struct rpcrdma_buffer	*rl_buffer;
 	struct rpcrdma_rep	*rl_reply;
 	struct xdr_stream	rl_stream;
@@ -357,16 +358,10 @@ enum {
 	RPCRDMA_REQ_F_TX_RESOURCES,
 };
 
-static inline void
-rpcrdma_set_xprtdata(struct rpc_rqst *rqst, struct rpcrdma_req *req)
-{
-	rqst->rq_xprtdata = req;
-}
-
 static inline struct rpcrdma_req *
 rpcr_to_rdmar(const struct rpc_rqst *rqst)
 {
-	return rqst->rq_xprtdata;
+	return container_of(rqst, struct rpcrdma_req, rl_slot);
 }
 
 static inline void
-- 
cgit v1.2.3


From 0e0b854cfb3302b1907e9d3a927469b95710238f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:14 -0400
Subject: xprtrdma: Clean up Receive trace points

For clarity, report the posting and completion of Receive CQEs.

Also, the wc->byte_len field contains garbage if wc->status is
non-zero, and the vendor error field contains garbage if wc->status
is zero. For readability, don't save those fields in those cases.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 62baddefced3..4b18926de912 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -160,7 +160,7 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 					       rr_cqe);
 
 	/* WARNING: Only wr_id and status are reliable at this point */
-	trace_xprtrdma_wc_receive(rep, wc);
+	trace_xprtrdma_wc_receive(wc);
 	if (wc->status != IB_WC_SUCCESS)
 		goto out_fail;
 
@@ -1570,7 +1570,7 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
 	if (!rpcrdma_dma_map_regbuf(ia, rep->rr_rdmabuf))
 		goto out_map;
 	rc = ib_post_recv(ia->ri_id->qp, &rep->rr_recv_wr, &recv_wr_fail);
-	trace_xprtrdma_post_recv(rep, rc);
+	trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe);
 	if (rc)
 		return -ENOTCONN;
 	return 0;
-- 
cgit v1.2.3


From 7c8d9e7c8863905951d4eaa7a8d277150f3a37f7 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:20 -0400
Subject: xprtrdma: Move Receive posting to Receive handler

Receive completion and Reply handling are done by a BOUND
workqueue, meaning they run on only one CPU.

Posting receives is currently done in the send_request path, which
on large systems is typically done on a different CPU than the one
handling Receive completions. This results in movement of
Receive-related cachelines between the sending and receiving CPUs.

More importantly, it means that currently Receives are posted while
the transport's write lock is held, which is unnecessary and costly.

Finally, allocation of Receive buffers is performed on-demand in
the Receive completion handler. This helps guarantee that they are
allocated on the same NUMA node as the CPU that handles Receive
completions.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/backchannel.c |  32 ++-----
 net/sunrpc/xprtrdma/rpc_rdma.c    |  22 ++---
 net/sunrpc/xprtrdma/transport.c   |   3 -
 net/sunrpc/xprtrdma/verbs.c       | 176 +++++++++++++++++++++-----------------
 net/sunrpc/xprtrdma/xprt_rdma.h   |   6 +-
 5 files changed, 115 insertions(+), 124 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 4034788c9856..c8f1c2b89dad 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -71,23 +71,6 @@ out_fail:
 	return -ENOMEM;
 }
 
-/* Allocate and add receive buffers to the rpcrdma_buffer's
- * existing list of rep's. These are released when the
- * transport is destroyed.
- */
-static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt,
-				 unsigned int count)
-{
-	int rc = 0;
-
-	while (count--) {
-		rc = rpcrdma_create_rep(r_xprt);
-		if (rc)
-			break;
-	}
-	return rc;
-}
-
 /**
  * xprt_rdma_bc_setup - Pre-allocate resources for handling backchannel requests
  * @xprt: transport associated with these backchannel resources
@@ -116,14 +99,6 @@ int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs)
 	if (rc)
 		goto out_free;
 
-	rc = rpcrdma_bc_setup_reps(r_xprt, reqs);
-	if (rc)
-		goto out_free;
-
-	rc = rpcrdma_ep_post_extra_recv(r_xprt, reqs);
-	if (rc)
-		goto out_free;
-
 	r_xprt->rx_buf.rb_bc_srv_max_requests = reqs;
 	request_module("svcrdma");
 	trace_xprtrdma_cb_setup(r_xprt, reqs);
@@ -228,6 +203,7 @@ int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst)
 	if (rc < 0)
 		goto failed_marshal;
 
+	rpcrdma_post_recvs(r_xprt, true);
 	if (rpcrdma_ep_post(&r_xprt->rx_ia, &r_xprt->rx_ep, req))
 		goto drop_connection;
 	return 0;
@@ -268,10 +244,14 @@ void xprt_rdma_bc_destroy(struct rpc_xprt *xprt, unsigned int reqs)
  */
 void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst)
 {
+	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	struct rpc_xprt *xprt = rqst->rq_xprt;
 
 	dprintk("RPC:       %s: freeing rqst %p (req %p)\n",
-		__func__, rqst, rpcr_to_rdmar(rqst));
+		__func__, rqst, req);
+
+	rpcrdma_recv_buffer_put(req->rl_reply);
+	req->rl_reply = NULL;
 
 	spin_lock_bh(&xprt->bc_pa_lock);
 	list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list);
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 8f89e3faae8e..d676106295ff 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1027,8 +1027,6 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 
 out_short:
 	pr_warn("RPC/RDMA short backward direction call\n");
-	if (rpcrdma_ep_post_recv(&r_xprt->rx_ia, rep))
-		xprt_disconnect_done(&r_xprt->rx_xprt);
 	return true;
 }
 #else	/* CONFIG_SUNRPC_BACKCHANNEL */
@@ -1334,13 +1332,14 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	u32 credits;
 	__be32 *p;
 
+	--buf->rb_posted_receives;
+
 	if (rep->rr_hdrbuf.head[0].iov_len == 0)
 		goto out_badstatus;
 
+	/* Fixed transport header fields */
 	xdr_init_decode(&rep->rr_stream, &rep->rr_hdrbuf,
 			rep->rr_hdrbuf.head[0].iov_base);
-
-	/* Fixed transport header fields */
 	p = xdr_inline_decode(&rep->rr_stream, 4 * sizeof(*p));
 	if (unlikely(!p))
 		goto out_shortreply;
@@ -1379,17 +1378,10 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 
 	trace_xprtrdma_reply(rqst->rq_task, rep, req, credits);
 
+	rpcrdma_post_recvs(r_xprt, false);
 	queue_work(rpcrdma_receive_wq, &rep->rr_work);
 	return;
 
-out_badstatus:
-	rpcrdma_recv_buffer_put(rep);
-	if (r_xprt->rx_ep.rep_connected == 1) {
-		r_xprt->rx_ep.rep_connected = -EIO;
-		rpcrdma_conn_func(&r_xprt->rx_ep);
-	}
-	return;
-
 out_badversion:
 	trace_xprtrdma_reply_vers(rep);
 	goto repost;
@@ -1409,7 +1401,7 @@ out_shortreply:
  * receive buffer before returning.
  */
 repost:
-	r_xprt->rx_stats.bad_reply_count++;
-	if (rpcrdma_ep_post_recv(&r_xprt->rx_ia, rep))
-		rpcrdma_recv_buffer_put(rep);
+	rpcrdma_post_recvs(r_xprt, false);
+out_badstatus:
+	rpcrdma_recv_buffer_put(rep);
 }
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 79885aa39c24..0c775f05123c 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -722,9 +722,6 @@ xprt_rdma_send_request(struct rpc_task *task)
 	if (rc < 0)
 		goto failed_marshal;
 
-	if (req->rl_reply == NULL) 		/* e.g. reconnection */
-		rpcrdma_recv_buffer_get(req);
-
 	/* Must suppress retransmit to maintain credits */
 	if (rqst->rq_connect_cookie == xprt->connect_cookie)
 		goto drop_connection;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 4b18926de912..2ed2ee4f2c6c 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -74,6 +74,7 @@
  */
 static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt);
 static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf);
+static int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt, bool temp);
 static void rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb);
 
 struct workqueue_struct *rpcrdma_receive_wq __read_mostly;
@@ -726,7 +727,6 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
 	struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt,
 						   rx_ia);
-	unsigned int extras;
 	int rc;
 
 retry:
@@ -770,9 +770,8 @@ retry:
 	}
 
 	dprintk("RPC:       %s: connected\n", __func__);
-	extras = r_xprt->rx_buf.rb_bc_srv_max_requests;
-	if (extras)
-		rpcrdma_ep_post_extra_recv(r_xprt, extras);
+
+	rpcrdma_post_recvs(r_xprt, true);
 
 out:
 	if (rc)
@@ -1082,14 +1081,8 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt)
 	return req;
 }
 
-/**
- * rpcrdma_create_rep - Allocate an rpcrdma_rep object
- * @r_xprt: controlling transport
- *
- * Returns 0 on success or a negative errno on failure.
- */
-int
-rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt)
+static int
+rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt, bool temp)
 {
 	struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
@@ -1117,6 +1110,7 @@ rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt)
 	rep->rr_recv_wr.wr_cqe = &rep->rr_cqe;
 	rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
 	rep->rr_recv_wr.num_sge = 1;
+	rep->rr_temp = temp;
 
 	spin_lock(&buf->rb_lock);
 	list_add(&rep->rr_list, &buf->rb_recv_bufs);
@@ -1168,12 +1162,8 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt)
 		list_add(&req->rl_list, &buf->rb_send_bufs);
 	}
 
+	buf->rb_posted_receives = 0;
 	INIT_LIST_HEAD(&buf->rb_recv_bufs);
-	for (i = 0; i <= buf->rb_max_requests; i++) {
-		rc = rpcrdma_create_rep(r_xprt);
-		if (rc)
-			goto out;
-	}
 
 	rc = rpcrdma_sendctxs_create(r_xprt);
 	if (rc)
@@ -1263,7 +1253,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 		rep = rpcrdma_buffer_get_rep_locked(buf);
 		rpcrdma_destroy_rep(rep);
 	}
-	buf->rb_send_count = 0;
 
 	spin_lock(&buf->rb_reqslock);
 	while (!list_empty(&buf->rb_allreqs)) {
@@ -1278,7 +1267,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 		spin_lock(&buf->rb_reqslock);
 	}
 	spin_unlock(&buf->rb_reqslock);
-	buf->rb_recv_count = 0;
 
 	rpcrdma_mrs_destroy(buf);
 }
@@ -1351,27 +1339,11 @@ rpcrdma_mr_unmap_and_put(struct rpcrdma_mr *mr)
 	__rpcrdma_mr_put(&r_xprt->rx_buf, mr);
 }
 
-static struct rpcrdma_rep *
-rpcrdma_buffer_get_rep(struct rpcrdma_buffer *buffers)
-{
-	/* If an RPC previously completed without a reply (say, a
-	 * credential problem or a soft timeout occurs) then hold off
-	 * on supplying more Receive buffers until the number of new
-	 * pending RPCs catches up to the number of posted Receives.
-	 */
-	if (unlikely(buffers->rb_send_count < buffers->rb_recv_count))
-		return NULL;
-
-	if (unlikely(list_empty(&buffers->rb_recv_bufs)))
-		return NULL;
-	buffers->rb_recv_count++;
-	return rpcrdma_buffer_get_rep_locked(buffers);
-}
-
-/*
- * Get a set of request/reply buffers.
+/**
+ * rpcrdma_buffer_get - Get a request buffer
+ * @buffers: Buffer pool from which to obtain a buffer
  *
- * Reply buffer (if available) is attached to send buffer upon return.
+ * Returns a fresh rpcrdma_req, or NULL if none are available.
  */
 struct rpcrdma_req *
 rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
@@ -1379,23 +1351,21 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
 	struct rpcrdma_req *req;
 
 	spin_lock(&buffers->rb_lock);
-	if (list_empty(&buffers->rb_send_bufs))
-		goto out_reqbuf;
-	buffers->rb_send_count++;
+	if (unlikely(list_empty(&buffers->rb_send_bufs)))
+		goto out_noreqs;
 	req = rpcrdma_buffer_get_req_locked(buffers);
-	req->rl_reply = rpcrdma_buffer_get_rep(buffers);
 	spin_unlock(&buffers->rb_lock);
-
 	return req;
 
-out_reqbuf:
+out_noreqs:
 	spin_unlock(&buffers->rb_lock);
 	return NULL;
 }
 
-/*
- * Put request/reply buffers back into pool.
- * Pre-decrement counter/array index.
+/**
+ * rpcrdma_buffer_put - Put request/reply buffers back into pool
+ * @req: object to return
+ *
  */
 void
 rpcrdma_buffer_put(struct rpcrdma_req *req)
@@ -1406,27 +1376,16 @@ rpcrdma_buffer_put(struct rpcrdma_req *req)
 	req->rl_reply = NULL;
 
 	spin_lock(&buffers->rb_lock);
-	buffers->rb_send_count--;
-	list_add_tail(&req->rl_list, &buffers->rb_send_bufs);
+	list_add(&req->rl_list, &buffers->rb_send_bufs);
 	if (rep) {
-		buffers->rb_recv_count--;
-		list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
+		if (!rep->rr_temp) {
+			list_add(&rep->rr_list, &buffers->rb_recv_bufs);
+			rep = NULL;
+		}
 	}
 	spin_unlock(&buffers->rb_lock);
-}
-
-/*
- * Recover reply buffers from pool.
- * This happens when recovering from disconnect.
- */
-void
-rpcrdma_recv_buffer_get(struct rpcrdma_req *req)
-{
-	struct rpcrdma_buffer *buffers = req->rl_buffer;
-
-	spin_lock(&buffers->rb_lock);
-	req->rl_reply = rpcrdma_buffer_get_rep(buffers);
-	spin_unlock(&buffers->rb_lock);
+	if (rep)
+		rpcrdma_destroy_rep(rep);
 }
 
 /*
@@ -1438,10 +1397,13 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
 {
 	struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf;
 
-	spin_lock(&buffers->rb_lock);
-	buffers->rb_recv_count--;
-	list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
-	spin_unlock(&buffers->rb_lock);
+	if (!rep->rr_temp) {
+		spin_lock(&buffers->rb_lock);
+		list_add(&rep->rr_list, &buffers->rb_recv_bufs);
+		spin_unlock(&buffers->rb_lock);
+	} else {
+		rpcrdma_destroy_rep(rep);
+	}
 }
 
 /**
@@ -1537,13 +1499,6 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	struct ib_send_wr *send_wr = &req->rl_sendctx->sc_wr;
 	int rc;
 
-	if (req->rl_reply) {
-		rc = rpcrdma_ep_post_recv(ia, req->rl_reply);
-		if (rc)
-			return rc;
-		req->rl_reply = NULL;
-	}
-
 	if (!ep->rep_send_count ||
 	    test_bit(RPCRDMA_REQ_F_TX_RESOURCES, &req->rl_flags)) {
 		send_wr->send_flags |= IB_SEND_SIGNALED;
@@ -1618,3 +1573,70 @@ out_rc:
 	rpcrdma_recv_buffer_put(rep);
 	return rc;
 }
+
+/**
+ * rpcrdma_post_recvs - Maybe post some Receive buffers
+ * @r_xprt: controlling transport
+ * @temp: when true, allocate temp rpcrdma_rep objects
+ *
+ */
+void
+rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
+{
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+	struct ib_recv_wr *wr, *bad_wr;
+	int needed, count, rc;
+
+	needed = buf->rb_credits + (buf->rb_bc_srv_max_requests << 1);
+	if (buf->rb_posted_receives > needed)
+		return;
+	needed -= buf->rb_posted_receives;
+
+	count = 0;
+	wr = NULL;
+	while (needed) {
+		struct rpcrdma_regbuf *rb;
+		struct rpcrdma_rep *rep;
+
+		spin_lock(&buf->rb_lock);
+		rep = list_first_entry_or_null(&buf->rb_recv_bufs,
+					       struct rpcrdma_rep, rr_list);
+		if (likely(rep))
+			list_del(&rep->rr_list);
+		spin_unlock(&buf->rb_lock);
+		if (!rep) {
+			if (rpcrdma_create_rep(r_xprt, temp))
+				break;
+			continue;
+		}
+
+		rb = rep->rr_rdmabuf;
+		if (!rpcrdma_regbuf_is_mapped(rb)) {
+			if (!__rpcrdma_dma_map_regbuf(&r_xprt->rx_ia, rb)) {
+				rpcrdma_recv_buffer_put(rep);
+				break;
+			}
+		}
+
+		trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe);
+		rep->rr_recv_wr.next = wr;
+		wr = &rep->rr_recv_wr;
+		++count;
+		--needed;
+	}
+	if (!count)
+		return;
+
+	rc = ib_post_recv(r_xprt->rx_ia.ri_id->qp, wr, &bad_wr);
+	if (rc) {
+		for (wr = bad_wr; wr; wr = wr->next) {
+			struct rpcrdma_rep *rep;
+
+			rep = container_of(wr, struct rpcrdma_rep, rr_recv_wr);
+			rpcrdma_recv_buffer_put(rep);
+			--count;
+		}
+	}
+	buf->rb_posted_receives += count;
+	trace_xprtrdma_post_recvs(r_xprt, count, rc);
+}
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 1d7bb6e5db18..4915a6dd58c9 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -197,6 +197,7 @@ struct rpcrdma_rep {
 	__be32			rr_proc;
 	int			rr_wc_flags;
 	u32			rr_inv_rkey;
+	bool			rr_temp;
 	struct rpcrdma_regbuf	*rr_rdmabuf;
 	struct rpcrdma_xprt	*rr_rxprt;
 	struct work_struct	rr_work;
@@ -397,11 +398,11 @@ struct rpcrdma_buffer {
 	struct rpcrdma_sendctx	**rb_sc_ctxs;
 
 	spinlock_t		rb_lock;	/* protect buf lists */
-	int			rb_send_count, rb_recv_count;
 	struct list_head	rb_send_bufs;
 	struct list_head	rb_recv_bufs;
 	u32			rb_max_requests;
 	u32			rb_credits;	/* most recent credit grant */
+	int			rb_posted_receives;
 
 	u32			rb_bc_srv_max_requests;
 	spinlock_t		rb_reqslock;	/* protect rb_allreqs */
@@ -558,13 +559,13 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *);
 int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *,
 				struct rpcrdma_req *);
 int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_rep *);
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
 
 /*
  * Buffer calls - xprtrdma/verbs.c
  */
 struct rpcrdma_req *rpcrdma_create_req(struct rpcrdma_xprt *);
 void rpcrdma_destroy_req(struct rpcrdma_req *);
-int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt);
 int rpcrdma_buffer_create(struct rpcrdma_xprt *);
 void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
 struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf);
@@ -577,7 +578,6 @@ void rpcrdma_mr_defer_recovery(struct rpcrdma_mr *mr);
 
 struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
 void rpcrdma_buffer_put(struct rpcrdma_req *);
-void rpcrdma_recv_buffer_get(struct rpcrdma_req *);
 void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
 
 struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(size_t, enum dma_data_direction,
-- 
cgit v1.2.3


From a7986f09986ac1befc85bcab30970312c476dbc7 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:25 -0400
Subject: xprtrdma: Remove rpcrdma_ep_{post_recv, post_extra_recv}

Clean up: These functions are no longer used.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c     | 59 -----------------------------------------
 net/sunrpc/xprtrdma/xprt_rdma.h |  3 ---
 2 files changed, 62 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 2ed2ee4f2c6c..601b78b64483 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1515,65 +1515,6 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	return 0;
 }
 
-int
-rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
-		     struct rpcrdma_rep *rep)
-{
-	struct ib_recv_wr *recv_wr_fail;
-	int rc;
-
-	if (!rpcrdma_dma_map_regbuf(ia, rep->rr_rdmabuf))
-		goto out_map;
-	rc = ib_post_recv(ia->ri_id->qp, &rep->rr_recv_wr, &recv_wr_fail);
-	trace_xprtrdma_post_recv(rep->rr_recv_wr.wr_cqe);
-	if (rc)
-		return -ENOTCONN;
-	return 0;
-
-out_map:
-	pr_err("rpcrdma: failed to DMA map the Receive buffer\n");
-	return -EIO;
-}
-
-/**
- * rpcrdma_ep_post_extra_recv - Post buffers for incoming backchannel requests
- * @r_xprt: transport associated with these backchannel resources
- * @count: minimum number of incoming requests expected
- *
- * Returns zero if all requested buffers were posted, or a negative errno.
- */
-int
-rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *r_xprt, unsigned int count)
-{
-	struct rpcrdma_buffer *buffers = &r_xprt->rx_buf;
-	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
-	struct rpcrdma_rep *rep;
-	int rc;
-
-	while (count--) {
-		spin_lock(&buffers->rb_lock);
-		if (list_empty(&buffers->rb_recv_bufs))
-			goto out_reqbuf;
-		rep = rpcrdma_buffer_get_rep_locked(buffers);
-		spin_unlock(&buffers->rb_lock);
-
-		rc = rpcrdma_ep_post_recv(ia, rep);
-		if (rc)
-			goto out_rc;
-	}
-
-	return 0;
-
-out_reqbuf:
-	spin_unlock(&buffers->rb_lock);
-	trace_xprtrdma_noreps(r_xprt);
-	return -ENOMEM;
-
-out_rc:
-	rpcrdma_recv_buffer_put(rep);
-	return rc;
-}
-
 /**
  * rpcrdma_post_recvs - Maybe post some Receive buffers
  * @r_xprt: controlling transport
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 4915a6dd58c9..44a31246b8f7 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -558,7 +558,6 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *);
 
 int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *,
 				struct rpcrdma_req *);
-int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_rep *);
 void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
 
 /*
@@ -599,8 +598,6 @@ rpcrdma_dma_map_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb)
 	return __rpcrdma_dma_map_regbuf(ia, rb);
 }
 
-int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int);
-
 int rpcrdma_alloc_wq(void);
 void rpcrdma_destroy_wq(void);
 
-- 
cgit v1.2.3


From e68699cc1a025d24608cf1533abc2edd7256d82c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:31 -0400
Subject: xprtrdma: Remove rpcrdma_buffer_get_req_locked()

Clean up. There is only one call-site for this helper, and it can be
simplified by using list_first_entry_or_null().

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c | 22 ++++------------------
 1 file changed, 4 insertions(+), 18 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 601b78b64483..b9a6e5d8d8c7 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1175,17 +1175,6 @@ out:
 	return rc;
 }
 
-static struct rpcrdma_req *
-rpcrdma_buffer_get_req_locked(struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_req *req;
-
-	req = list_first_entry(&buf->rb_send_bufs,
-			       struct rpcrdma_req, rl_list);
-	list_del_init(&req->rl_list);
-	return req;
-}
-
 static struct rpcrdma_rep *
 rpcrdma_buffer_get_rep_locked(struct rpcrdma_buffer *buf)
 {
@@ -1351,15 +1340,12 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
 	struct rpcrdma_req *req;
 
 	spin_lock(&buffers->rb_lock);
-	if (unlikely(list_empty(&buffers->rb_send_bufs)))
-		goto out_noreqs;
-	req = rpcrdma_buffer_get_req_locked(buffers);
+	req = list_first_entry_or_null(&buffers->rb_send_bufs,
+				       struct rpcrdma_req, rl_list);
+	if (req)
+		list_del_init(&req->rl_list);
 	spin_unlock(&buffers->rb_lock);
 	return req;
-
-out_noreqs:
-	spin_unlock(&buffers->rb_lock);
-	return NULL;
 }
 
 /**
-- 
cgit v1.2.3


From 9d95cd534ca1ce969ff3f87d6e8ca6a9dfd1ad04 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:36 -0400
Subject: xprtrdma: Remove rpcrdma_buffer_get_rep_locked()

Clean up: There is only one remaining call site for this helper.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index b9a6e5d8d8c7..db11aa04c612 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1175,17 +1175,6 @@ out:
 	return rc;
 }
 
-static struct rpcrdma_rep *
-rpcrdma_buffer_get_rep_locked(struct rpcrdma_buffer *buf)
-{
-	struct rpcrdma_rep *rep;
-
-	rep = list_first_entry(&buf->rb_recv_bufs,
-			       struct rpcrdma_rep, rr_list);
-	list_del(&rep->rr_list);
-	return rep;
-}
-
 static void
 rpcrdma_destroy_rep(struct rpcrdma_rep *rep)
 {
@@ -1239,7 +1228,9 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 	while (!list_empty(&buf->rb_recv_bufs)) {
 		struct rpcrdma_rep *rep;
 
-		rep = rpcrdma_buffer_get_rep_locked(buf);
+		rep = list_first_entry(&buf->rb_recv_bufs,
+				       struct rpcrdma_rep, rr_list);
+		list_del(&rep->rr_list);
 		rpcrdma_destroy_rep(rep);
 	}
 
-- 
cgit v1.2.3


From efd81e90d3f719a2a7fd696c9ed0247e1cae1b7c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:41 -0400
Subject: xprtrdma: Make rpcrdma_sendctx_put_locked() a static function

Clean up: The only call site is in the same file as the function's
definition.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/verbs.c     | 4 +++-
 net/sunrpc/xprtrdma/xprt_rdma.h | 1 -
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index db11aa04c612..0e0b7d5cb74d 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -72,6 +72,7 @@
 /*
  * internal functions
  */
+static void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc);
 static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt);
 static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf);
 static int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt, bool temp);
@@ -949,7 +950,8 @@ out_emptyq:
  *
  * The caller serializes calls to this function (per rpcrdma_buffer).
  */
-void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc)
+static void
+rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc)
 {
 	struct rpcrdma_buffer *buf = &sc->sc_xprt->rx_buf;
 	unsigned long next_tail;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 44a31246b8f7..c60687934092 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -568,7 +568,6 @@ void rpcrdma_destroy_req(struct rpcrdma_req *);
 int rpcrdma_buffer_create(struct rpcrdma_xprt *);
 void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
 struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf);
-void rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc);
 
 struct rpcrdma_mr *rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt);
 void rpcrdma_mr_put(struct rpcrdma_mr *mr);
-- 
cgit v1.2.3


From a8f688ec437dc2045cc8f0c89fe877d5803850da Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:46 -0400
Subject: xprtrdma: Return -ENOBUFS when no pages are available

The use of -EAGAIN in rpcrdma_convert_iovs() is a latent bug: the
transport never calls xprt_write_space() when more pages become
available. -ENOBUFS will trigger the correct "delay briefly and call
again" logic.

Fixes: 7a89f9c626e3 ("xprtrdma: Honor ->send_request API contract")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: stable@vger.kernel.org # 4.8+
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index d676106295ff..1d7857919d3d 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -231,7 +231,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 			 */
 			*ppages = alloc_page(GFP_ATOMIC);
 			if (!*ppages)
-				return -EAGAIN;
+				return -ENOBUFS;
 		}
 		seg->mr_page = *ppages;
 		seg->mr_offset = (char *)page_base;
-- 
cgit v1.2.3


From ed3aa7424566f35c51035748928575a35625e07e Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:52 -0400
Subject: xprtrdma: Move common wait_for_buffer_space call to parent function

Clean up: The logic to wait for write space is common to a bunch of
the encoding helper functions. Lift it out and put it in the tail
of rpcrdma_marshal_req().

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c | 31 ++++++++++++-------------------
 1 file changed, 12 insertions(+), 19 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 1d7857919d3d..b12b0443d33a 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -366,7 +366,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
 						   false, &mr);
 		if (IS_ERR(seg))
-			goto out_maperr;
+			return PTR_ERR(seg);
 		rpcrdma_mr_push(mr, &req->rl_registered);
 
 		if (encode_read_segment(xdr, mr, pos) < 0)
@@ -378,11 +378,6 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	} while (nsegs);
 
 	return 0;
-
-out_maperr:
-	if (PTR_ERR(seg) == -EAGAIN)
-		xprt_wait_for_buffer_space(rqst->rq_task, NULL);
-	return PTR_ERR(seg);
 }
 
 /* Register and XDR encode the Write list. Supports encoding a list
@@ -429,7 +424,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
 						   true, &mr);
 		if (IS_ERR(seg))
-			goto out_maperr;
+			return PTR_ERR(seg);
 		rpcrdma_mr_push(mr, &req->rl_registered);
 
 		if (encode_rdma_segment(xdr, mr) < 0)
@@ -446,11 +441,6 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	*segcount = cpu_to_be32(nchunks);
 
 	return 0;
-
-out_maperr:
-	if (PTR_ERR(seg) == -EAGAIN)
-		xprt_wait_for_buffer_space(rqst->rq_task, NULL);
-	return PTR_ERR(seg);
 }
 
 /* Register and XDR encode the Reply chunk. Supports encoding an array
@@ -492,7 +482,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 		seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs,
 						   true, &mr);
 		if (IS_ERR(seg))
-			goto out_maperr;
+			return PTR_ERR(seg);
 		rpcrdma_mr_push(mr, &req->rl_registered);
 
 		if (encode_rdma_segment(xdr, mr) < 0)
@@ -509,11 +499,6 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req,
 	*segcount = cpu_to_be32(nchunks);
 
 	return 0;
-
-out_maperr:
-	if (PTR_ERR(seg) == -EAGAIN)
-		xprt_wait_for_buffer_space(rqst->rq_task, NULL);
-	return PTR_ERR(seg);
 }
 
 /**
@@ -884,7 +869,15 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst)
 	return 0;
 
 out_err:
-	r_xprt->rx_stats.failed_marshal_count++;
+	switch (ret) {
+	case -EAGAIN:
+		xprt_wait_for_buffer_space(rqst->rq_task, NULL);
+		break;
+	case -ENOBUFS:
+		break;
+	default:
+		r_xprt->rx_stats.failed_marshal_count++;
+	}
 	return ret;
 }
 
-- 
cgit v1.2.3


From 2fad659209d5b1dbaa1f58606372571c61fc8cbd Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:35:57 -0400
Subject: xprtrdma: Wait on empty sendctx queue

Currently, when the sendctx queue is exhausted during marshaling, the
RPC/RDMA transport places the RPC task on the delayq, which forces a
wait for HZ >> 2 before the marshal and send is retried.

With this change, the transport now places such an RPC task on the
pending queue, and wakes it just as soon as more sendctxs become
available. This typically takes less than a millisecond, and the
write_space waking mechanism is less deadlock-prone.

Moreover, the waiting RPC task is holding the transport's write
lock, which blocks the transport from sending RPCs. Therefore faster
recovery from sendctx queue exhaustion is desirable.

Cf. commit 5804891455d5 ("xprtrdma: ->send_request returns -EAGAIN
when there are no free MRs").

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c  | 2 +-
 net/sunrpc/xprtrdma/verbs.c     | 8 +++++++-
 net/sunrpc/xprtrdma/xprt_rdma.h | 6 ++++++
 3 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index b12b0443d33a..a373d0322a80 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -695,7 +695,7 @@ rpcrdma_prepare_send_sges(struct rpcrdma_xprt *r_xprt,
 {
 	req->rl_sendctx = rpcrdma_sendctx_get_locked(&r_xprt->rx_buf);
 	if (!req->rl_sendctx)
-		return -ENOBUFS;
+		return -EAGAIN;
 	req->rl_sendctx->sc_wr.num_sge = 0;
 	req->rl_sendctx->sc_unmap_count = 0;
 	req->rl_sendctx->sc_req = req;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 0e0b7d5cb74d..7276e82db3b4 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -878,6 +878,7 @@ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt)
 		sc->sc_xprt = r_xprt;
 		buf->rb_sc_ctxs[i] = sc;
 	}
+	buf->rb_flags = 0;
 
 	return 0;
 
@@ -935,7 +936,7 @@ out_emptyq:
 	 * completions recently. This is a sign the Send Queue is
 	 * backing up. Cause the caller to pause and try again.
 	 */
-	dprintk("RPC:       %s: empty sendctx queue\n", __func__);
+	set_bit(RPCRDMA_BUF_F_EMPTY_SCQ, &buf->rb_flags);
 	r_xprt = container_of(buf, struct rpcrdma_xprt, rx_buf);
 	r_xprt->rx_stats.empty_sendctx_q++;
 	return NULL;
@@ -970,6 +971,11 @@ rpcrdma_sendctx_put_locked(struct rpcrdma_sendctx *sc)
 
 	/* Paired with READ_ONCE */
 	smp_store_release(&buf->rb_sc_tail, next_tail);
+
+	if (test_and_clear_bit(RPCRDMA_BUF_F_EMPTY_SCQ, &buf->rb_flags)) {
+		smp_mb__after_atomic();
+		xprt_write_space(&sc->sc_xprt->rx_xprt);
+	}
 }
 
 static void
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index c60687934092..e4a408d7b195 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -400,6 +400,7 @@ struct rpcrdma_buffer {
 	spinlock_t		rb_lock;	/* protect buf lists */
 	struct list_head	rb_send_bufs;
 	struct list_head	rb_recv_bufs;
+	unsigned long		rb_flags;
 	u32			rb_max_requests;
 	u32			rb_credits;	/* most recent credit grant */
 	int			rb_posted_receives;
@@ -417,6 +418,11 @@ struct rpcrdma_buffer {
 };
 #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia)
 
+/* rb_flags */
+enum {
+	RPCRDMA_BUF_F_EMPTY_SCQ = 0,
+};
+
 /*
  * Internal structure for transport instance creation. This
  * exists primarily for modularity.
-- 
cgit v1.2.3


From 8335640cf89faa0f4e39e73e314f3f3a22d776f3 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:36:02 -0400
Subject: xprtrdma: Add trace_xprtrdma_dma_map(mr)

Matches trace_xprtrdma_dma_unmap(mr).

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/fmr_ops.c  | 1 +
 net/sunrpc/xprtrdma/frwr_ops.c | 1 +
 2 files changed, 2 insertions(+)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 592d1e8e27c3..d2bc82f577b0 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -244,6 +244,7 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 				     mr->mr_sg, i, mr->mr_dir);
 	if (!mr->mr_nents)
 		goto out_dmamap_err;
+	trace_xprtrdma_dma_map(mr);
 
 	for (i = 0, dma_pages = mr->fmr.fm_physaddrs; i < mr->mr_nents; i++)
 		dma_pages[i] = sg_dma_address(&mr->mr_sg[i]);
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 0f2e108d387e..3056dc901be0 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -418,6 +418,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 	mr->mr_nents = ib_dma_map_sg(ia->ri_device, mr->mr_sg, i, mr->mr_dir);
 	if (!mr->mr_nents)
 		goto out_dmamap_err;
+	trace_xprtrdma_dma_map(mr);
 
 	ibmr = frwr->fr_mr;
 	n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE);
-- 
cgit v1.2.3


From 11d0ac16b02eab8cda32efcb51bfab452dab760b Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 May 2018 15:36:08 -0400
Subject: xprtrdma: Remove transfertypes array

Clean up: This array was used in a dprintk that was replaced by a
trace point in commit ab03eff58eb5 ("xprtrdma: Add trace points in
RPC Call transmit paths").

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 net/sunrpc/xprtrdma/rpc_rdma.c | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'net/sunrpc/xprtrdma')

diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index a373d0322a80..1c78516aa6f2 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -55,14 +55,6 @@
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-static const char transfertypes[][12] = {
-	"inline",	/* no chunks */
-	"read list",	/* some argument via rdma read */
-	"*read list",	/* entire request via rdma read */
-	"write list",	/* some result via rdma write */
-	"reply chunk"	/* entire reply via rdma write */
-};
-
 /* Returns size of largest RPC-over-RDMA header in a Call message
  *
  * The largest Call header contains a full-size Read list and a
-- 
cgit v1.2.3