IB/isert: Properly release resources on DEVICE_REMOVAL

When the low level driver exercises the hot unplug they would call
rdma_cm cma_remove_one which would fire DEVICE_REMOVAL event to all cma
consumers. Now, if consumer doesn't make sure they destroy all IB
objects created on that IB device instance prior to finalizing all
processing of DEVICE_REMOVAL callback, rdma_cm will let the lld to
de-register with IB core and destroy the IB device instance. And if the
consumer calls (say) ib_dereg_mr(), it will crash since that dev object
is NULL.

In the current implementation, iser-target just initiates the cleanup
and returns from DEVICE_REMOVAL callback. This deferred work creates a
race between iser-target cleaning IB objects(say MR) and lld destroying
IB device instance.

This patch includes the following fixes
  -> make sure that consumer frees all IB objects associated with device
     instance
  -> return non-zero from the callback to destroy the rdma_cm id

Signed-off-by: Raju Rangoju <rajur@chelsio.com>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>

2 files changed, 22 insertions, 3 deletions

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 7914c14478cd..cae9bbcc27e7 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -403,6 +403,7 @@ isert_init_conn(struct isert_conn *isert_conn)
 	INIT_LIST_HEAD(&isert_conn->node);
 	init_completion(&isert_conn->login_comp);
 	init_completion(&isert_conn->login_req_comp);
+	init_waitqueue_head(&isert_conn->rem_wait);
 	kref_init(&isert_conn->kref);
 	mutex_init(&isert_conn->mutex);
 	INIT_WORK(&isert_conn->release_work, isert_release_work);
@@ -578,7 +579,8 @@ isert_connect_release(struct isert_conn *isert_conn)
 	BUG_ON(!device);
 
 	isert_free_rx_descriptors(isert_conn);
-	if (isert_conn->cm_id)
+	if (isert_conn->cm_id &&
+	    !isert_conn->dev_removed)
 		rdma_destroy_id(isert_conn->cm_id);
 
 	if (isert_conn->qp) {
@@ -593,7 +595,10 @@ isert_connect_release(struct isert_conn *isert_conn)
 
 	isert_device_put(device);
 
-	kfree(isert_conn);
+	if (isert_conn->dev_removed)
+		wake_up_interruptible(&isert_conn->rem_wait);
+	else
+		kfree(isert_conn);
 }
 
 static void
@@ -753,6 +758,7 @@ static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	struct isert_np *isert_np = cma_id->context;
+	struct isert_conn *isert_conn;
 	int ret = 0;
 
 	isert_info("%s (%d): status %d id %p np %p\n",
@@ -773,10 +779,21 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 		break;
 	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
-	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
 		ret = isert_disconnected_handler(cma_id, event->event);
 		break;
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+		isert_conn = cma_id->qp->qp_context;
+		isert_conn->dev_removed = true;
+		isert_disconnected_handler(cma_id, event->event);
+		wait_event_interruptible(isert_conn->rem_wait,
+					 isert_conn->state == ISER_CONN_DOWN);
+		kfree(isert_conn);
+		/*
+		 * return non-zero from the callback to destroy
+		 * the rdma cm id
+		 */
+		return 1;
 	case RDMA_CM_EVENT_REJECTED:       /* FALLTHRU */
 	case RDMA_CM_EVENT_UNREACHABLE:    /* FALLTHRU */
 	case RDMA_CM_EVENT_CONNECT_ERROR:
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index fc791efe3a10..c02ada57d7f5 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -158,6 +158,8 @@ struct isert_conn {
 	struct work_struct	release_work;
 	bool                    logout_posted;
 	bool                    snd_w_inv;
+	wait_queue_head_t	rem_wait;
+	bool			dev_removed;
 };
 
 #define ISERT_MAX_CQ 64