Back from PTO
As people know, I've had some paternity leave here as of late. Then there was the annual shutdown at Red Hat for the holidays, and then I had some PTO on the back end of that. As a result, I've been absent for a while. I don't like to pre-announce these things on public mailing lists (nothing like telling the whole world when you will be away from home to make you feel safe about your home while you're gone), but I don't mind letting people know where I've been now that I'm back.
Obviously I'm behind. I'm going to send in a pull request shortly with the things that I had before I left on break. I didn't get everything into my for-next tag that I wanted to before I left on break, so I expect there will be a second pull request that includes at least a couple larger items I was working on when I left that should be about the same now as they were before:
RoCEv2 support
mlx5 RoCE support
mlx4 RoCEv2 support
rdmavtqib->rdmavt changes
Things that I intended to submit after the merge window opened and Greg's merge was done:
Retake staging/rdma
Delete staging/rdma/{amso1100,ehca,ipath}hfi1->rdmavt changes
Add staging/rdma/soft-rxe
Along the way, I may pick up some other commits too. If you haven't seen your desired commit(s) that you think should make it into 4.5 (like the [v2] IB/core: sysfs.c: Fix PerfMgt ClassPortInfo handling patch that isn't in yet but needs to be), please send me an email *offlist* (this is important for my mail filtering that the list not be in the to/cc address, you can bcc if you want) and include a link to the patch or patches, preferably as a link to the latest version in patchworks versus say a link to a mailing list archive of the submission email.
Thanks!
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD
A message that is not in the archive (sent off-list or not yet received): [email protected]
Quoted 21 lines · Doug Ledford
As people know, I've had some paternity leave here as of late. Then there was the annual shutdown at Red Hat for the holidays, and then I had some PTO on the back end of that. As a result, I've been absent for a while. I don't like to pre-announce these things on public mailing lists (nothing like telling the whole world when you will be away from home to make you feel safe about your home while you're gone), but I don't mind letting people know where I've been now that I'm back.
Obviously I'm behind. I'm going to send in a pull request shortly with the things that I had before I left on break. I didn't get everything into my for-next tag that I wanted to before I left on break, so I expect there will be a second pull request that includes at least a couple larger items I was working on when I left that should be about the same now as they were before:
RoCEv2 support
mlx5 RoCE support
mlx4 RoCEv2 support
rdmavtqib->rdmavtchanges
Quoted 8 lines
Things that I intended to submit after the merge window opened and Greg's merge was done:
Retake staging/rdma
Delete staging/rdma/{amso1100,ehca,ipath}hfi1->rdmavtchanges
Add staging/rdma/soft-rxe
Doug,
it's not clear if you intend to take rdmavt into drivers/infiniband/sw IMHO such a central piece of code needs to go through proper design stages, be written with a clear and sharp interface and be published with documentation.
To me it looks like the only purpose of rdmavt is to pull hfi1 driver out from staging. If we want it as an infrastructure for any kind of low level driver it needs to stick to infrastructure standards. I hope that you agree
Quoted 9 lines
Along the way, I may pick up some other commits too. If you haven't seen your desired commit(s) that you think should make it into 4.5 (like the [v2] IB/core:
sysfs.c: Fix PerfMgt ClassPortInfo handling patch that isn't in yet but needs to be), please send me an email *offlist* (this is important for my mail filtering that the list not be in the to/cc address, you can bcc if you want) and include a link to the patch or patches, preferably as a link to the latest version in patchworks versus say a link to a mailing list archive of the submission email.
Quoted 7 lines
Thanks!
--
Doug Ledford <[email protected]>GPG KeyID: 0E572FDD
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): CAG9sBKP8kqax_wqyej+1J+hFaaCUFKdFyAX8e4Hxg3HoafWjrg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org
Quoted 8 lines · Moni Shoua
Quoted 6 lines · Doug Ledford
rdmavt
qib->rdmavtchangesThings that I intended to submit after the merge window opened and Greg's merge was done:
Quoted 7 lines
Quoted 5 lines
Retake staging/rdma
Delete staging/rdma/{amso1100,ehca,ipath}hfi1->rdmavtchanges
Add staging/rdma/soft-rxeDoug,
it's not clear if you intend to take rdmavt intodrivers/infiniband/sw
I had intended to. However, on Jan 6th at roughly 1pm EST, Dennis submitted v3 of his rdmavt patch set. At roughly 2pm EST you submitted a completely different, competing patchset that resides in the same place in the filesystem, has the same name, but is 100% different internally. I know Intel and Mellanox have a hard time working together, but geeze...
Quoted 3 lines
IMHO such a central piece of code needs to go through proper design stages, be written with a clear and sharp interface and be published with documentation.
Yes, you've repeated this multiple times. As this is a kernel internal interface only, and a private one to the IB stack, we can be a bit more flexible than you suggest here and do things a little more on the fly.
Quoted 2 lines
To me it looks like the only purpose of rdmavt is to pull hfi1 driver out from staging.
That's obviously the piece that Intel cares about, sure.
Quoted 2 lines
If we want it as an infrastructure for any kind of low level driver it needs to stick to infrastructure standards.
This statement is too vague for me to say anything constructive.
Quoted 1 line
I hope that you agree
Again, too vague to answer.
Signature · 2 lines
Doug Ledford <[email protected]> GPG KeyID: 0E572FDD