mbox series

[for-rc,0/3] IB/hfi1: Fixes for 5.2 RC cycle

Message ID 20190607113807.157915.48581.stgit@awfm-01.aw.intel.com (mailing list archive)
Headers show
Series IB/hfi1: Fixes for 5.2 RC cycle | expand

Message

Dennis Dalessandro June 7, 2019, 11:39 a.m. UTC
We have a couple of fixes we'd like to try and get into the rc cycle. These 3
are all targeted to stable as well. One fixes an issue of not validating user
input that was reported by Dan C. We have a race condition that leads to a
hung SDMA engine as well as a fix for a problem when verbs and kdeth packets
get processed on different cpus for the same qp.

---

Kaike Wan (1):
      IB/hfi1: Validate fault injection opcode user input

Mike Marciniszyn (2):
      IB/hfi1: Close PSM sdma_progress sleep window
      IB/hfi1: Correct tid qp rcd to match verbs context


 drivers/infiniband/hw/hfi1/chip.c      |   13 +++++++++++++
 drivers/infiniband/hw/hfi1/chip.h      |    1 +
 drivers/infiniband/hw/hfi1/fault.c     |    5 +++++
 drivers/infiniband/hw/hfi1/fault.h     |    6 +++---
 drivers/infiniband/hw/hfi1/tid_rdma.c  |    5 ++---
 drivers/infiniband/hw/hfi1/user_sdma.c |   12 ++++--------
 drivers/infiniband/hw/hfi1/user_sdma.h |    1 -
 7 files changed, 28 insertions(+), 15 deletions(-)

--
-Denny

Comments

Jason Gunthorpe June 11, 2019, 8:11 p.m. UTC | #1
On Fri, Jun 07, 2019 at 07:39:05AM -0400, Dennis Dalessandro wrote:
> We have a couple of fixes we'd like to try and get into the rc cycle. These 3
> are all targeted to stable as well. One fixes an issue of not validating user
> input that was reported by Dan C. We have a race condition that leads to a
> hung SDMA engine as well as a fix for a problem when verbs and kdeth packets
> get processed on different cpus for the same qp.
> 
> 
> Kaike Wan (1):
>       IB/hfi1: Validate fault injection opcode user input
> 
> Mike Marciniszyn (2):
>       IB/hfi1: Close PSM sdma_progress sleep window
>       IB/hfi1: Correct tid qp rcd to match verbs context

Applied to for-rc, thanks

Jason