linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Oded Gabbay <oded.gabbay@gmail.com>
To: gregkh@linuxfoundation.org
Cc: linux-kernel@vger.kernel.org
Subject: [git pull] habanalabs fixes pull request for kernel 5.8-rc4/5
Date: Fri, 10 Jul 2020 20:03:22 +0300	[thread overview]
Message-ID: <20200710170322.GA29124@ogabbay-VM> (raw)

Hello Greg,

This pull request is for the next rc (rc4 or 5) and it contains:

1. Important bug fix for the GAUDI command parsing code.

2. Change in debugfs interface that is relevant only for GAUDI and
   therefore can still be changed in this release.

3. Workaround for a timeout problem in GOYA and GAUDI.

Details are in the tag message below.

Thanks,
Oded

The following changes since commit 897c44f0bae574c5fb318c759b060bebf9dd6013:

  virtio: virtio_console: add missing MODULE_DEVICE_TABLE() for rproc serial (2020-07-10 15:12:48 +0200)

are available in the Git repository at:

  git://people.freedesktop.org/~gabbayo/linux tags/misc-habanalabs-fixes-2020-07-10

for you to fetch changes up to 788cacf308871db0a619952321bedfec8f1773e2:

  habanalabs: set 4s timeout for message to device CPU (2020-07-10 19:53:03 +0300)

----------------------------------------------------------------
This tag contains the following fixes for 5.8-rc4/5:

- Prevent user from using command WREG_BULK in PCI DMA channel. The command
  won't be parsed correctly by the driver and will cause unknown behavior.
  As the user doesn't need to use that command in that channel, its better
  to just prevent it completely.

- Change the interface of the clock gating debugfs property from true/false
  to bitmask with bit per engine. This will allow the user to debug the
  ASIC while disabling the clock gating feature with fine-grain
  granularity.

- Increase message-to-ASIC-CPU timeout to 4s (from 100ms/1s). The ASIC CPU
  might respond sometimes after a large delay due to slow external
  interfaces (such as temperature sensors) and that will result in a driver
  timeout which will lead to ASIC reset.

----------------------------------------------------------------
Oded Gabbay (3):
      habanalabs: block WREG_BULK packet on PDMA
      habanalabs: set clock gating per engine
      habanalabs: set 4s timeout for message to device CPU

 .../ABI/testing/debugfs-driver-habanalabs          |  11 +-
 drivers/misc/habanalabs/debugfs.c                  |  23 ++--
 drivers/misc/habanalabs/device.c                   |   2 +-
 drivers/misc/habanalabs/firmware_if.c              |  10 +-
 drivers/misc/habanalabs/gaudi/gaudi.c              | 123 ++++++++++++++-------
 drivers/misc/habanalabs/goya/goya.c                |  20 ++--
 drivers/misc/habanalabs/habanalabs.h               |  19 +++-
 drivers/misc/habanalabs/habanalabs_drv.c           |   2 +-
 drivers/misc/habanalabs/hwmon.c                    |  19 ++--
 drivers/misc/habanalabs/sysfs.c                    |  11 +-
 10 files changed, 147 insertions(+), 93 deletions(-)

             reply	other threads:[~2020-07-10 17:03 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-10 17:03 Oded Gabbay [this message]
2020-07-17  9:57 ` [git pull] habanalabs fixes pull request for kernel 5.8-rc4/5 Greg KH

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200710170322.GA29124@ogabbay-VM \
    --to=oded.gabbay@gmail.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).