Commit 4aa16152 authored by Jason Gunthorpe's avatar Jason Gunthorpe
Browse files

RDMA/core: Fix ordering of CQ pool destruction

rxe will hold a refcount on the IB device as long as CQ objects exist,
this causes destruction of a rxe device to hang if the CQ pool has any
cached CQs since they are being destroyed after the refcount must go to
zero.

Treat the CQ pool like a client and create/destroy it before/after all
other clients. No users of CQ pool can exist past a client remove call.

Link: https://lore.kernel.org/r/e8a240aa-9e9b-3dca-062f-9130b787f29b@acm.org


Fixes: c7ff819a ("RDMA/core: Introduce shared CQ pool API")
Tested-by: default avatarBart Van Assche <bvanassche@acm.org>
Tested-by: default avatarYi Zhang <yi.zhang@redhat.com>
Signed-off-by: default avatarBart Van Assche <bvanassche@acm.org>
Signed-off-by: default avatarJason Gunthorpe <jgg@nvidia.com>
parent 856deb86
Loading
Loading
Loading
Loading
+4 −2
Original line number Diff line number Diff line
@@ -1285,6 +1285,8 @@ static void disable_device(struct ib_device *device)
		remove_client_context(device, cid);
	}

	ib_cq_pool_destroy(device);

	/* Pairs with refcount_set in enable_device */
	ib_device_put(device);
	wait_for_completion(&device->unreg_completion);
@@ -1328,6 +1330,8 @@ static int enable_device_and_get(struct ib_device *device)
			goto out;
	}

	ib_cq_pool_init(device);

	down_read(&clients_rwsem);
	xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) {
		ret = add_client_context(device, client);
@@ -1400,7 +1404,6 @@ int ib_register_device(struct ib_device *device, const char *name)
		goto dev_cleanup;
	}

	ib_cq_pool_init(device);
	ret = enable_device_and_get(device);
	dev_set_uevent_suppress(&device->dev, false);
	/* Mark for userspace that device is ready */
@@ -1455,7 +1458,6 @@ static void __ib_unregister_device(struct ib_device *ib_dev)
		goto out;

	disable_device(ib_dev);
	ib_cq_pool_destroy(ib_dev);

	/* Expedite removing unregistered pointers from the hash table */
	free_netdevs(ib_dev);