> The intent is to cover the user space component of the kernel. > > So, if code is including uapi/rdma/* then it is a good candidate for > this tree. Based on discussions so far, I would limit the scope to the 'common' or 'shared' or non-vendor-specific areas of the uAPI. > libacm, I am unclear on. Is it the recommended userspace component for > the netlink socket that Kaike? Is it coupled to librdmacm? If yes it > should probably come too. Yes, this is the userspace daemon for the SA netlink socket. And to be clear, it's ibacm, as it's a daemon not a library. The librdmacm looks for and uses ibacm when present. > psm/psm2, I have no knowledge about this, it seems to meet the > qualification, but I haven't seen it follow a community model? I > don't have an impression that Intel would view that favorably.. I couldn't say for certain, but my guess is that the psm team would like to maintain this separately. AFAIK, it has no dependency on verbs or the verbs uapi. > opensm is not qualified since it rides on the other libraries. > > Not sure what distributed SA encompasses.. I'm not sure either at this point. It used to ride completely on the other libraries. -- 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