[ofa-general] IB function calls in kernel module fail

[Tziporet Koren]

neutron wrote:
> Hi all,
>
> I'm writing a kernel module that make use of basic IB verbs to
> communicate, like:
> ib_register_client,  ib_unregister_client,  ib_alloc_pd,
> ib_create_qp,  ib_reg_phys_mr,  etc.
>
> I can compile the code into a kernel module:  ib_rdma_lat.ko.   This
> module is to test the RDMA write latency from kernel module.
>
> But when I "insmod", I got error reports at /var/log/messages:
>
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_unregister_client
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_unregister_client
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_create_cq
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_create_cq
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_reg_phys_mr
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_reg_phys_mr
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_dereg_mr
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_dereg_mr
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_register_client
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_register_client
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_destroy_cq
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_destroy_cq
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_query_port
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_query_port
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_alloc_pd
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_alloc_pd
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_create_qp
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_create_qp
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_modify_qp
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_modify_qp
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_destroy_qp
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_destroy_qp
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: disagrees about version of
> symbol ib_dealloc_pd
> Feb 15 16:33:28 wci11 kernel: ib_rdma_lat: Unknown symbol ib_dealloc_pd
>
> I'm running rhel5.  I have rebooted the node many times but didn't
> help at all.
>
>   
 From OFED_tips:
4. External Module Compilation Over OFED-1.4
===============================================================================

To build kernel modules depending on OFED's modules, take the 
Modules.symvers
file from <prefix>/src/openib/Module.symvers (part of the 
kernel-ib-devel RPM)
and copy it to the modules subdir and then compile your module.

If <prefix>/src/openib/Module.symvers does not exist or it is empty, use the
create_Module.symvers.sh (a part of the ofed-docs RPM) script to create the
Module.symvers file.

See "Module versioning & Module.symvers" in the modules.txt from kernel
documentation (e.g. linux-2.6.20/Documentation/kbuild/modules.txt).


Tziporet