All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniel Vetter <daniel@ffwll.ch>
To: Oded Gabbay <ogabbay@kernel.org>
Cc: airlied@gmail.com, daniel.vetter@ffwll.ch,
	dri-devel@lists.freedesktop.org
Subject: Re: [git pull] habanalabs for drm-next-6.9
Date: Mon, 26 Feb 2024 11:33:33 +0100	[thread overview]
Message-ID: <Zdxo_VVrs4mkjUI-@phenom.ffwll.local> (raw)
In-Reply-To: <ZdxJprop0EniVQtf@ogabbay-vm-u22.habana-labs.com>

On Mon, Feb 26, 2024 at 10:19:50AM +0200, Oded Gabbay wrote:
> Hi Dave, Sima.
> 
> Habanalabs pull request for 6.9.
> 
> No uapi changes this time. Just minor features, improvements, code cleanups
> and bug fixes. Also one small change in accel subsystem file.
> 
> Full details are in the signed tag.
> 
> Thanks,
> Oded
> 
> The following changes since commit 40d47c5fb4f2a7c1ef168598f01bdcbd31ba4038:
> 
>   Merge tag 'amd-drm-next-6.9-2024-02-19' of https://gitlab.freedesktop.org/agd5f/linux into drm-next (2024-02-22 13:21:19 +1000)
> 
> are available in the Git repository at:
> 
>   https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux.git tags/drm-habanalabs-next-2024-02-26
> 
> for you to fetch changes up to 576d7cc5a9e29e4cc579ffb0f9afc209e34eea31:
> 
>   accel: constify the struct device_type usage (2024-02-26 09:59:18 +0200)

Pulled into drm-next, thanks a lot!
-Sima

> 
> ----------------------------------------------------------------
> This tag contains habanalabs driver and accel changes for v6.9.
> 
> The notable changes are:
> 
> - New features and improvements:
>   - Configure interrupt affinity according to NUMA nodes for the MSI-X interrupts that are
>     assigned to the userspace application which acquires the device.
>   - Move the HBM MMU page tables to reside inside the HBM to minimize latency when doing
>     page-walks.
>   - Improve the device reset mechanism when consecutive heartbeat failures occur (firmware
>     fails to ack on heartbeat message).
>   - Check also extended errors in the PCIe addr_dec interrupt information.
>   - Rate limit the error messages that can be printed to dmesg log by userspace actions.
> 
> - Firmware related fixes:
>   - Handle requests from firmware to reserve device memory
> 
> - Bug fixes and code cleanups:
>   - constify the struct device_type usage in accel (accel_sysfs_device_minor).
>   - Fix the PCI health check by reading uncached register.
>   - Fix reporting of drain events.
>   - Fix debugfs files permissions.
>   - Fix calculation of DRAM BAR base address.
> 
> ----------------------------------------------------------------
> Avri Kehat (1):
>       accel/habanalabs: fix debugfs files permissions
> 
> Colin Ian King (1):
>       accel/habanalabs/goya: remove redundant assignment to pointer 'input'
> 
> Dani Liberman (3):
>       accel/habanalabs/gaudi2: add interrupt affinity for user interrupts
>       accel/habanalabs: remove call to deprecated function
>       accel/habanalabs: fix error print
> 
> Erick Archer (1):
>       accel/habanalabs: use kcalloc() instead of kzalloc()
> 
> Farah Kassabri (2):
>       accel/habanalabs/gaudi2: move HMMU page tables to device memory
>       accel/habanalabs: remove hop size from asic properties
> 
> Koby Elbaz (1):
>       accel/habanalabs: increase HL_MAX_STR to 64 bytes to avoid warnings
> 
> Malkoot Khan (1):
>       accel/habanalabs: Remove unnecessary braces from if statement
> 
> Ofir Bitton (3):
>       accel/habanalabs/gaudi2: drain event lacks rd/wr indication
>       accel/habanalabs/hwmon: rate limit errors user can generate
>       accel/habanalabs: modify pci health check
> 
> Ricardo B. Marliere (1):
>       accel: constify the struct device_type usage
> 
> Tal Risin (1):
>       accel/habanalabs: initialize maybe-uninitialized variables
> 
> Tomer Tayar (8):
>       accel/habanalabs: fix DRAM BAR base address calculation
>       accel/habanalabs: abort device reset for consecutive heartbeat failures
>       accel/habanalabs/gaudi2: fail memory memset when failing to copy QM packet to device
>       accel/habanalabs: modify print for skip loading linux FW to debug log
>       accel/habanalabs/gaudi2: check extended errors according to PCIe addr_dec interrupt info
>       accel/habanalabs: fix glbl error cause handling
>       accel/habanalabs: handle reserved memory request when working with full FW
>       accel/habanalabs: keep explicit size of reserved memory for FW
> 
>  drivers/accel/drm_accel.c                          |   2 +-
>  .../accel/habanalabs/common/command_submission.c   |   3 +-
>  drivers/accel/habanalabs/common/debugfs.c          |  18 +-
>  drivers/accel/habanalabs/common/device.c           |  55 +++-
>  drivers/accel/habanalabs/common/firmware_if.c      |  25 +-
>  drivers/accel/habanalabs/common/habanalabs.h       |  43 ++-
>  drivers/accel/habanalabs/common/hw_queue.c         |  17 +
>  drivers/accel/habanalabs/common/hwmon.c            |  29 +-
>  drivers/accel/habanalabs/common/mmu/Makefile       |   2 +-
>  drivers/accel/habanalabs/common/mmu/mmu.c          | 223 ++++++++++++-
>  drivers/accel/habanalabs/common/mmu/mmu_v1.c       | 354 +++------------------
>  drivers/accel/habanalabs/common/mmu/mmu_v2.c       | 338 ++++++++++++++++++++
>  drivers/accel/habanalabs/common/mmu/mmu_v2_hr.c    |  24 +-
>  drivers/accel/habanalabs/common/security.c         |  33 +-
>  drivers/accel/habanalabs/common/security.h         |   3 +-
>  drivers/accel/habanalabs/gaudi/gaudi.c             |   9 +-
>  drivers/accel/habanalabs/gaudi2/gaudi2.c           | 308 ++++++++++++------
>  drivers/accel/habanalabs/gaudi2/gaudi2P.h          |  15 +-
>  drivers/accel/habanalabs/goya/goya.c               |  12 +-
>  drivers/accel/habanalabs/goya/goya_coresight.c     |   3 +-
>  .../habanalabs/include/hw_ip/mmu/mmu_general.h     |   2 +
>  21 files changed, 1008 insertions(+), 510 deletions(-)
>  create mode 100644 drivers/accel/habanalabs/common/mmu/mmu_v2.c

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch

      reply	other threads:[~2024-02-26 10:33 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-26  8:19 [git pull] habanalabs for drm-next-6.9 Oded Gabbay
2024-02-26 10:33 ` Daniel Vetter [this message]

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=Zdxo_VVrs4mkjUI-@phenom.ffwll.local \
    --to=daniel@ffwll.ch \
    --cc=airlied@gmail.com \
    --cc=daniel.vetter@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=ogabbay@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.