On Wed, 2018-05-02 at 06:42 -0700, Dennis Dalessandro wrote:
> Hi Doug and Jason,
>
> Here are some patches to go to for-next. These include the couple patches that
> needed rework that were posted before the OFA conf. Well actually those patches
> that had issues were just dropped with the exception of the one from Alex, to
> add handling of kernel restart to hfi1 and qib. Patch 8 is his V2.
>
> Nothing else too scary or exciting in here. Well OK so that's not quite right
> the CQ completion vector patch is rather interesting. This adds support
> for compeltion vectors for hfi1 and helps improve performance in things like
> IPoIB.
>
> There is a signifianct patch from Mitko that redoes a lof our fault injection
> stuff. It's a big patch but I'm not sure it lends itself to being broken up
> further.
>
> One other thing of note is the "Create common functions" patch from Sebastian
> depends on one of the patches that I sent for the -rc. It won't apply cleanly
> without that.
>
> ---
>
> Alex Estrin (2):
> IB/hfi1: Complete check for locally terminated smp
> IB/{hfi1,qib}: Add handling of kernel restart
>
> Brian Welty (1):
> IB/{hfi1,qib,rdmavt}: Move logic to allocate receive WQE into rdmavt
>
> Kamenee Arumugam (1):
> IB/Hfi1: Read CCE Revision register to verify the device is responsive
>
> Michael J. Ruhl (4):
> IB/hfi1: Return actual error value from program_rcvarray()
> IB/hfi1: Use after free race condition in send context error path
> IB/hfi1: Return correct value for device state
> IB/hfi1: Reorder incorrect send context disable
>
> Mike Marciniszyn (1):
> IB/hfi1: Fix fault injection init/exit issues
>
> Mitko Haralanov (1):
> IB/hfi1: Rework fault injection machinery
>
> Sebastian Sanchez (4):
> IB/hfi1: Prevent LNI hang when LCB can't obtain lanes
> IB/hfi1: Optimize kthread pointer locking when queuing CQ entries
> IB/hfi1: Create common functions for affinity CPU mask operations
> IB/{hfi1,rdmavt,qib}: Implement CQ completion vector support
>
Hi Denny,
As mentioned, I pulled patch 5 of this series into for-rc, and I pulled
the rest into for-next last week. Thanks.
--
Doug Ledford <dledford@xxxxxxxxxx>
GPG KeyID: B826A3330E572FDD
Key fingerprint = AE6B 1BDA 122B 23B4 265B 1274 B826 A333 0E57 2FDDAttachment:
signature.asc
Description: This is a digitally signed message part
