From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH for-next 00/13] IB/hfi1,core: Driver updates for 4.17 Date: Tue, 17 Apr 2018 19:40:53 -0600 Message-ID: <20180418014053.GA10098@ziepe.ca> References: <20180405025915.18766.41569.stgit@scvm10.sc.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20180405025915.18766.41569.stgit@scvm10.sc.intel.com> Sender: stable-owner@vger.kernel.org To: Dennis Dalessandro Cc: dledford@redhat.com, Mike Mariciniszyn , linux-rdma@vger.kernel.org, Mitko Haralanov , Brian Welty , Alex Estrin , stable@vger.kernel.org, Ashutosh Dixit , "Michael J. Ruhl" , Harish Chegondi , Don Hiatt , Sebastian Sanchez , Prathap Kumar Valsan List-Id: linux-rdma@vger.kernel.org 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