On Wed, Apr 04, 2018 at 08:01:11PM -0700, Dennis Dalessandro wrote:
> Hi Jason and Doug,
>
> Here are most of our updates for 4.17. I will follow this up with a small
> 16B series then I still have a few more patches that are waiting on
> some more thorough testing. Should be able to get them on the list tomrrow or
> Friday at the latest, wanted to get these out now. I don't think anything
> is really that scary in here.
>
> These are mostly driver fixes. Patches 4,7,8,11, and 14 are marked stable.
> They didn't get sent for the -rc because they fix really old issues.
>
> Patch 5 is a core fix. I should have sent it a bit sooner, sorry about that but
> it's pretty trivial so I decided to include it as well rather than wait for
> 4.18.
>
>
> Alex Estrin (2):
> IB/hfi1: Complete check for locally terminated smp
> IB/{hfi1,qib}: Add handling of kernel restart
>
> Ashutosh Dixit (1):
> IB/core: Fix rkey invalidation from user space into the kernel
>
> Michael J. Ruhl (5):
> IB/hfi1: Return actual error value from program_rcvarray()
> IB/hfi1: Use after free race condition in send context error path
> IB/hfi1 Use correct type for num_user_context
> IB/hfi1: Return correct value for device state
> IB/hfi1: Reorder incorrect send context disable
>
> Mike Marciniszyn (3):
> IB/hfi1: Fix handling of FECN marked multicast packet
> IB/hfi1: Fix fault injection init/exit issues
> IB/hfi1: Fix loss of BECN with AHG
>
> Sebastian Sanchez (2):
> IB/hfi1: Prevent LNI hang when LCB can't obtain lanes
> IB/{hfi1,rdmavt,qib}: Fit kernel completions into single aligned cache-line
Many of these got comments so I'm just going to drop the
series. Please rebase and resend anything you think should go to -rc
or -next that doesn't interact with the patches being revised.
Also let me know if the next '16B' series is independent of this, if
yes I'll drop it to..
Jason