On Thu, Dec 24, 2015 at 06:22:14PM +0200, eran ben elisha wrote: > On Mon, Dec 21, 2015 at 4:20 PM, Christoph Lameter <cl@xxxxxxxxx> wrote: [snip] > > > > +/* > > + * Figure out which counter table to use depending on > > + * the device capabilities. > > + */ > > +static struct attribute_group *get_counter_table(struct ib_device *dev) > > +{ > > + struct ib_class_port_info cpi; > > + > > + if (get_perf_mad(dev, 0, IB_PMA_CLASS_PORT_INFO, > > Why 0, need to pass port num. > See proposal Matan and myself sent. > Passing a port num to a ClassPortInfo query makes no sense? Your proposal sets a field which is wrong (I think it sets part of TrapGID if my math is correct) in the ClassPortInfo query as per the spec. I think the fix needs to be somewhere else. Ira -- 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