On 04/05/2018 12:21 AM, Jason Gunthorpe wrote: > On Wed, Apr 04, 2018 at 10:26:47AM +0200, Nicolas Morey-Chaisemartin wrote: >> ib_umad is required to get ibstat working. >> Auto-load it for RoCE hardware so it works out of the box >> >> $ ibstat >> ibwarn: [4638] umad_init: can't read ABI version from /sys/class/infiniband_mad/abi_version (No such file or directory): is ib_umad module loaded? >> ibpanic: [4638] main: can't init UMAD library: No such file or directory >> $ modprobe ib_umad >> $ ibstat >> CA 'bnxt_re0' >> CA type: Broadcom NetXtreme-C/E RoCE Driver HCA >> Number of ports: 1 >> Firmware version: 20.8.29.0 >> Hardware version: 0x14e4 >> Node GUID: 0x9edc71fffeb69930 >> System image GUID: 0x9edc71fffeb69930 >> Port 1: >> State: Down >> Physical state: Disabled >> Rate: 100 >> Base lid: 0 >> LMC: 0 >> SM lid: 0 >> Capability mask: 0x041d0000 >> Port GUID: 0x9edc71fffeb69930 >> Link layer: Ethernet >> >> Signed-off-by: Nicolas Morey-Chaisemartin <nmoreychaisemartin@xxxxxxxx> >> --- >> kernel-boot/modules/roce.conf | 3 +++ >> 1 file changed, 3 insertions(+) > Is this just a userspace bug in ibstat or do roce ports actually implement umad? > > Jason It seems like they don't. It's just ibstat doing a umad_init() before making few calls to umad_get_cas_names() and a few other that seem to work through simple reads in sysfs (not umad related). Not sure what the clean way to fix this is. Removing the call to umad_init feels dirty but it's simple enough. Any ideas ? It might be worth updating the man pages to flag which umad function do not actually require the umad module and are safe to call without calling umad_init() first. Nicolas -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
