[PATCH 3/5] xprtrdma: Handle device removal outside of the CM event handler

[cel@kernel.org]

From: Chuck Lever <chuck.lever@oracle.com>

Wait for all disconnects to complete to ensure the transport has
divested all of its hardware resources before the underlying RDMA
device can be removed.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/trace/events/rpcrdma.h  | 23 +++++++++++++++++++++++
 net/sunrpc/xprtrdma/verbs.c     | 23 ++++++++++++++---------
 net/sunrpc/xprtrdma/xprt_rdma.h |  2 ++
 3 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index ecdaf088219d..ba2d6a0e41cc 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -669,6 +669,29 @@ TRACE_EVENT(xprtrdma_inline_thresh,
 DEFINE_CONN_EVENT(connect);
 DEFINE_CONN_EVENT(disconnect);
 
+TRACE_EVENT(xprtrdma_device_removal,
+	TP_PROTO(
+		const struct rdma_cm_id *id
+	),
+
+	TP_ARGS(id),
+
+	TP_STRUCT__entry(
+		__string(name, id->device->name)
+		__array(unsigned char, addr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		memcpy(__entry->addr, &id->route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("device %s to be removed, disconnecting %pISpc\n",
+		__get_str(name), __entry->addr
+	)
+);
+
 DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc);
 
 TRACE_EVENT(xprtrdma_op_connect,
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index a0b071089e15..04558c99e9f4 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -222,7 +222,6 @@ static void rpcrdma_update_cm_private(struct rpcrdma_ep *ep,
 static int
 rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 {
-	struct sockaddr *sap = (struct sockaddr *)&id->route.addr.dst_addr;
 	struct rpcrdma_ep *ep = id->context;
 
 	might_sleep();
@@ -241,14 +240,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 		ep->re_async_rc = -ENETUNREACH;
 		complete(&ep->re_done);
 		return 0;
-	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-		pr_info("rpcrdma: removing device %s for %pISpc\n",
-			ep->re_id->device->name, sap);
-		switch (xchg(&ep->re_connect_status, -ENODEV)) {
-		case 0: goto wake_connect_worker;
-		case 1: goto disconnected;
-		}
-		return 0;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
 		ep->re_connect_status = -ENODEV;
 		goto disconnected;
@@ -284,6 +275,14 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	return 0;
 }
 
+static void rpcrdma_ep_removal_done(struct rpcrdma_notification *rn)
+{
+	struct rpcrdma_ep *ep = container_of(rn, struct rpcrdma_ep, re_rn);
+
+	trace_xprtrdma_device_removal(ep->re_id);
+	xprt_force_disconnect(ep->re_xprt);
+}
+
 static struct rdma_cm_id *rpcrdma_create_id(struct rpcrdma_xprt *r_xprt,
 					    struct rpcrdma_ep *ep)
 {
@@ -323,6 +322,10 @@ static struct rdma_cm_id *rpcrdma_create_id(struct rpcrdma_xprt *r_xprt,
 	if (rc)
 		goto out;
 
+	rc = rpcrdma_rn_register(id->device, &ep->re_rn, rpcrdma_ep_removal_done);
+	if (rc)
+		goto out;
+
 	return id;
 
 out:
@@ -350,6 +353,8 @@ static void rpcrdma_ep_destroy(struct kref *kref)
 		ib_dealloc_pd(ep->re_pd);
 	ep->re_pd = NULL;
 
+	rpcrdma_rn_unregister(ep->re_id->device, &ep->re_rn);
+
 	kfree(ep);
 	module_put(THIS_MODULE);
 }
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index da409450dfc0..341725c66ec8 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -56,6 +56,7 @@
 #include <linux/sunrpc/rpc_rdma_cid.h> 	/* completion IDs */
 #include <linux/sunrpc/rpc_rdma.h> 	/* RPC/RDMA protocol */
 #include <linux/sunrpc/xprtrdma.h> 	/* xprt parameters */
+#include <linux/sunrpc/rdma_rn.h>	/* removal notifications */
 
 #define RDMA_RESOLVE_TIMEOUT	(5000)	/* 5 seconds */
 #define RDMA_CONNECT_RETRY_MAX	(2)	/* retries if no listener backlog */
@@ -92,6 +93,7 @@ struct rpcrdma_ep {
 	struct rpcrdma_connect_private
 				re_cm_private;
 	struct rdma_conn_param	re_remote_cma;
+	struct rpcrdma_notification	re_rn;
 	int			re_receive_count;
 	unsigned int		re_max_requests; /* depends on device */
 	unsigned int		re_inline_send;	/* negotiated */
-- 
2.45.1