On Wed, 2017-01-18 at 14:08 -0700, Jason Gunthorpe wrote: > On Wed, Jan 18, 2017 at 04:01:00PM -0500, Doug Ledford wrote: > > > > > OK, sure, as far as the reordering stuff is concerned, all you need > > to > > do is to make use of the EPROBE_DEFER return option to your PCI > > probe > > routine. That way, when you get the probe for the out of order > > port, > > EPROBE_DEFER is intended when waiting on other components the driver > may need, not for setting stable names. What it's intended for, and what it can be used for, need not be the same. > This is a 'stable device naming' problem, which we have never tried > to > solve in RDMA. No, that would imply they must be hfi1_0 and hfi1_1, when this is not the case. If you had two cards in this system, both dual port, then you may be wanting to rename hfi_3 to hfi1_2 and vice versa. It is a relative name problem, not a stable name problem. We need only reverse the order that the ports are probed in, their names are whatever they end up being once reversed. > udev is the expected kernel way to solve this. Trying to hack stable > names by forcing device bind order is horrible. This is a manufacturing defect. Something I'm sure Intel wants to resolve without requiring users to go in and manually name their ports. I have no doubt that they would prefer that the user remain blissfully unaware of the issue, all except for the ones that probably reported it and already have their system cabled up wrong as a result. > hfi runs smack into this because it is the first scheme to actually > typically operate in a multi-struct ib_device world, which means they > get to solve it properly :\ No, mlx5 could have easily hit this too as their ports are separate PCI functions. As I said, it's a manufacturing defect and that means I'm sure Intel would prefer to solve it silently and automatically. I would if I were them anyway. -- Doug Ledford <dledford@xxxxxxxxxx> GPG KeyID: B826A3330E572FDD Key fingerprint = AE6B 1BDA 122B 23B4 265B 1274 B826 A333 0E57 2FDD
Attachment:
signature.asc
Description: This is a digitally signed message part
