Documentation/userspace-api/media/glossary.rst:170: WARNING: duplicate term description of SPI, other instance in gpu/amdgpu/amdgpu-glossary
That's because SPI of amdgpu (Shader Processor Input) shares the same
global glossary term as SPI of media subsystem (which is Serial
Peripheral Interface Bus). Disambiguate the former from the latter to
fix the warning.
Note that adding context qualifiers in the term is strictly necessary
in order to make Sphinx happy.
Fixes: dd3d035a78 ("Documentation/gpu: Add new entries to amdgpu glossary")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/linux-next/20250509185845.60bf5e7b@canb.auug.org.au/
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add the register!() macro, which defines a given register's layout and
provide bit-field accessors with a way to convert them to a given type.
This macro will allow us to make clear definitions of the registers and
manipulate their fields safely.
The long-term goal is to eventually move it to the kernel crate so it
can be used by other drivers as well, but it was agreed to first land it
into nova-core and make it mature there.
To illustrate its usage, use it to define the layout for the Boot0
(renamed to NV_PMC_BOOT_0 to match OpenRM's naming scheme) and take
advantage of its accessors.
Suggested-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250507-nova-frts-v3-5-fcb02749754d@nvidia.com
[ Fix typo in commit message. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Add a description for the get_csb_buffer callback, update the glossary,
and add some extra information about RB, which is associated with CSB
configuration.
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add survivability mode document to pcode document as it is enabled
when pcode detects a failure.
v2: fix kernel-doc (Lucas)
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250407051414.1651616-3-riana.tauro@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Registers a configfs subsystem called 'xe' that creates a
directory in the mounted configfs directory (/sys/kernel/config)
Userspace can then create the device that has to be configured
under the xe directory
mkdir /sys/kernel/config/xe/0000:03:00.0
The device created will have the following attributes to be
configured
/sys/kernel/config/xe/
.. 0000:03:00.0/
... survivability_mode
v2: fix kernel-doc
fix return value (Lucas)
v3: fix kernel-doc (Lucas)
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250407051414.1651616-2-riana.tauro@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
This adds the UAPI for the Asahi driver targeting the GPU in the Apple
M1 and M2 series systems on chip. The UAPI design is based on other
modern Vulkan-capable drivers, including Xe and Panthor. Memory
management is based on explicit VM management. Synchronization is
exclusively explicit sync.
This UAPI is validated against our open source Mesa stack, which is
fully conformant to the OpenGL 4.6, OpenGL ES 3.2, OpenCL 3.0, and
Vulkan 1.4 standards. The Vulkan driver supports sparse, exercising the
VM_BIND mechanism.
This patch adds the standalone UAPI header. It is implemented by an open
source DRM driver written in Rust. We fully intend to upstream this
driver when possible. However, as a production graphics driver, it
depends on a significant number of Rust abstractions that will take a
long time to upstream. In the mean time, our userspace is upstream in
Mesa but is not allowed to probe with upstream Mesa as the UAPI is not
yet reviewed and merged in the upstream kernel. Although we ship a
patched Mesa in Fedora Asahi Remix, any containers shipping upstream
Mesa builds are broken for our users, including upstream Flatpak and
Waydroid runtimes. Additionally, it forces us to maintain forks of Mesa
and virglrenderer, which complicates bisects.
The intention in sending out this patch is for this UAPI to be
thoroughly reviewed. Once we as the DRM community are satisfied with the
UAPI, this header lands signifying that the UAPI is stable and must only
be evolved in backwards-compatible ways; it will be the UAPI implemented
in the DRM driver that eventually lands upstream. That promise lets us
enable upstream Mesa, solving all these issues while the upstream Rust
abstractions are developed.
https://github.com/alyssarosenzweig/linux/commits/agx-uapi-v7 contains
the DRM driver implementing this proposed UAPI.
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33984 contains
the Mesa patches to implement this proposed UAPI.
That Linux and Mesa branch together give a complete graphics/compute
stack on top of this UAPI.
Co-developed-by: Asahi Lina <lina@asahilina.net>
Signed-off-by: Asahi Lina <lina@asahilina.net>
Acked-by: Simona Vetter <simona.vetter@ffwll.ch>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Reviewed-by: Janne Grunau <j@jannau.net>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Link: https://lore.kernel.org/r/20250408-agx-uapi-v7-1-ad122d4f7324@rosenzweig.io
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
In reference to memory carved out for APUs,
s/cave out/carve out/
Reviewed-by: shaoyun.liu <Shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
MES is an important firmware that lacks some essential documentation.
This commit introduces an overview of it and how it works.
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
GC is a large block that plays a vital role for amdgpu; for this reason,
this commit creates one specific page for GC and adds extra information
about the CP component.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Pipes and Queues are two common vocabulary that pervades discussions
around amdgpu core features. The definition and explanation of those
components are spread around multiple places in the code, mailing list,
and Gitlab, which sometimes leads to the wrong interpretation of these
concepts. This commit attempts to centralize the definition and
explanation of Pipe and Queue from amdgpu perspective in a kernel doc.
Most of the information in this doc was derived from:
- https://lore.kernel.org/amd-gfx/CADnq5_Pcz2x4aJzKbVrN3jsZhD6sTydtDw=6PaN4O3m4t+Grtg@mail.gmail.com/T/#m9a670b55ab20e0f7c46c80f802a0a4be255a719d
- https://gitlab.freedesktop.org/mesa/mesa/-/issues/11759
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The APU and dGPU tables are hidden in the driver misc info, which makes
it hard to find specific hardware info when users need it. This commit
creates a single page for this information and adds it to the top of the
amdgpu list to improve searchability.
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Since driver-core has an overview of the AMD GPU hardware structure, it
makes more sense to keep it first. This commit move driver-core up in
the index list.
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit introduces some new acronyms extracted from the source code
and found on some web pages around the internet (most of them came from
ArchLinux, Gentoo, and Wikipedia links).
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Describes what debugfs files are available and what
they are used for.
v2: fix some typos (Mark Glines)
v3: Address comments from Siqueira and Kent
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Backmerging to get v6.15-rc1 into drm-misc-next. Also fixes a
build issue when enabling CONFIG_DRM_SCHED_KUNIT_TEST.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Due to wrong `.. kernel-doc` directive in Documentation/gpu/rfc/gpusvm.rst
the documentation was actually not parsing anything from
drivers/gpu/drm/drm_gpusvm.c. This fixes the kernel-doc include and all
warnings/errors created when doing so.
Cc: Simona Vetter <simona.vetter@ffwll.ch>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: dri-devel@lists.freedesktop.org
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/intel-xe/20250307195239.57abcd2d@canb.auug.org.au/
Fixes: 99624bdff8 ("drm/gpusvm: Add support for GPU Shared Virtual Memory")
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250307-fix-svm-kerneldoc-v2-1-03c74b199620@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 4da1fb61e0)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
We have enabled PROVE_LOCKING (which enables LOCKDEP) in drm-ci.
This will output warnings when kernel locking errors are encountered
and will continue executing tests. To detect if lockdep has been
triggered, check the debug_locks value in /proc/lockdep_stats after
the tests have run. When debug_locks is 0, it indicates that lockdep
has detected issues and turned itself off. Check this value, and if
lockdep is detected, exit with an error and configure it as a warning
in GitLab CI.
GitLab CI ignores exit codes other than 1 by default. Pass the correct
exit code with variable FF_USE_NEW_BASH_EVAL_STRATEGY set to true or
exit on failure.
Also update the documentation.
Acked-by: Helen Koike <helen.fornazier@gmail.com>
Reviewed-by: Daniel Stone <daniels@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250217053719.442644-4-vignesh.raman@collabora.com
Signed-off-by: Vignesh Raman <vignesh.raman@collabora.com>
- Expose per-engine activity via perf pmu (Riana, Lucas, Umesh)
- Add support for EU stall sampling (Harish, Ashutosh)
- Allow userspace to provide low latency hint for submission (Tejas)
- GPU SVM and Xe SVM implementation (Matthew Brost)
Cross-subsystem Changes:
- devres handling for component drivers (Lucas)
- Backmege drm-next to allow cross dependent change with i915
- GPU SVM and Xe SVM implementation (Matthew Brost)
Core Changes:
Driver Changes:
- Fixes to userptr and missing validations (Matthew Auld, Thomas
Hellström, Matthew Brost)
- devcoredump typos and error handling improvement (Shuicheng)
- Allow oa_exponent value of 0 (Umesh)
- Finish moving device probe to devm (Lucas)
- Fix race between submission restart and scheduled being freed (Tejas)
- Fix counter overflows in gt_stats (Francois)
- Refactor and add missing workarounds and tunings for pre-Xe2 platforms
(Aradhya, Tvrtko)
- Fix PXP locks interaction with exec queues being killed (Daniele)
- Eliminate TIMESTAMP_OVERRIDE from xe (Matt Roper)
- Change xe_gen_wa_oob to allow building on MacOS (Daniel Gomez)
- New workarounds for Panther Lake (Tejas)
- Fix VF resume errors (Satyanarayana)
- Fix workaround infra skipping some workarounds dependent on engine
initialization (Tvrtko)
- Improve per-IP descriptors (Gustavo)
- Add more error injections to probe sequence (Francois)
-----BEGIN PGP SIGNATURE-----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=98mS
-----END PGP SIGNATURE-----
Merge tag 'drm-xe-next-2025-03-07' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next
UAPI Changes:
- Expose per-engine activity via perf pmu (Riana, Lucas, Umesh)
- Add support for EU stall sampling (Harish, Ashutosh)
- Allow userspace to provide low latency hint for submission (Tejas)
- GPU SVM and Xe SVM implementation (Matthew Brost)
Cross-subsystem Changes:
- devres handling for component drivers (Lucas)
- Backmege drm-next to allow cross dependent change with i915
- GPU SVM and Xe SVM implementation (Matthew Brost)
Core Changes:
Driver Changes:
- Fixes to userptr and missing validations (Matthew Auld, Thomas
Hellström, Matthew Brost)
- devcoredump typos and error handling improvement (Shuicheng)
- Allow oa_exponent value of 0 (Umesh)
- Finish moving device probe to devm (Lucas)
- Fix race between submission restart and scheduled being freed (Tejas)
- Fix counter overflows in gt_stats (Francois)
- Refactor and add missing workarounds and tunings for pre-Xe2 platforms
(Aradhya, Tvrtko)
- Fix PXP locks interaction with exec queues being killed (Daniele)
- Eliminate TIMESTAMP_OVERRIDE from xe (Matt Roper)
- Change xe_gen_wa_oob to allow building on MacOS (Daniel Gomez)
- New workarounds for Panther Lake (Tejas)
- Fix VF resume errors (Satyanarayana)
- Fix workaround infra skipping some workarounds dependent on engine
initialization (Tvrtko)
- Improve per-IP descriptors (Gustavo)
- Add more error injections to probe sequence (Francois)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ilc5jvtyaoyi6woyhght5a6sw5jcluiojjueorcyxbynrcpcjp@mw2mi6rd6a7l
Update the Documentation to be more precise.
v2: Update for clarity
v3: Further details in Todo
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Anusha Srivatsa <asrivats@redhat.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/640856/?series=144073&rev=5
Add the initial documentation of the Nova project.
The initial project documentation consists out of a brief introduction
of the project, as well as project guidelines both general and nova-core
specific and a task list for nova-core specifically.
The task list is divided into tasks for general Rust infrastructure
required by the project, tasks regarding GSP enablement and firmware
abstraction, general GPU driver tasks as well as tasks related to
external API design and test infrastructure.
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250306222336.23482-6-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
There can be multiple cases of handling the GSP RPC messages, which are
the reply of GSP RPC commands according to the requirement of the
callers and the nature of the GSP RPC commands.
The current supported reply policies are "callers don't care" and "receive
the entire message" according to the requirement of the callers. To
introduce a new policy, factor out the current RPC command reply polices.
Also, centralize the handling of the reply in a single function.
Factor out NVKM_GSP_RPC_REPLY_NOWAIT as "callers don't care" and
NVKM_GSP_RPC_REPLY_RECV as "receive the entire message". Introduce a
kernel doc to document the policies. Factor out
r535_gsp_rpc_handle_reply().
No functional change is intended for small GSP RPC commands. For large GSP
commands, the caller decides the policy of how to handle the returned GSP
RPC message.
Cc: Ben Skeggs <bskeggs@nvidia.com>
Cc: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Zhi Wang <zhiw@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250227013554.8269-2-zhiw@nvidia.com
Add documentation for agree upon GPU SVM design principles, current
status, and future plans.
v4:
- Address Thomas's feedback
v5:
- s/Current/Basline (Thomas)
v7:
- Add license (CI)
- Add examples for design guideline reasoning (Alistair)
- Add snippet about possible livelock with concurrent GPU and and CPU
access (Alistair)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Alistair Popple <apopple@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-33-matthew.brost@intel.com
Some items were defined in both the general and DC glossaries.
Remove the duplicate entries.
Fixes: 2df30ae0ba ("Documentation/gpu: Add acronyms for some firmware components")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The DRM and KMS frameworks and helpers gain more and more kunit
coverage, so let's document what our expectations are.
Suggested-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Maíra Canal <mcanal@igalia.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Simona Vetter <simona.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20250113101100.1373856-1-mripard@kernel.org
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Users can check the file "/sys/kernel/debug/dri/0/amdgpu_firmware_info"
to get information on the firmware loaded in the system. This file has
multiple acronyms that are not documented in the glossary. This commit
introduces some missing acronyms to the AMD glossary documentation. The
meaning of each acronym in this commit was extracted from code
documentation available in the following files:
- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
- drivers/gpu/drm/amd/include/amd_shared.h
Changes since v1:
- Expand acronym meanings based on Alex Deucher suggestions.
Cc: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
A previous commit enabled display of driver-internal kernel BO sizes
through the device file's fdinfo interface.
Expand the description of the relevant driver-specific key:value pairs
with the definitions of the new panthor-*-memory ones.
Reviewed-by: Mihail Atanassov <mihail.atanassov@arm.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250130172851.941597-5-adrian.larumbe@collabora.com
This change reflects de facto usage by amdgpu, as exemplified by commit
d6530c33a9 ("drm/amdgpu: expose more memory stats in fdinfo").
Cc: Tvrtko Ursulin <tursulin@ursulin.net>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250130172851.941597-2-adrian.larumbe@collabora.com
In order to explain the name clean-ups in GSP RPC routines, a kernel
doc to explain the memory layout and terms is required.
Add a kernel doc to introduce the GSP RPC.
Cc: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Zhi Wang <zhiw@nvidia.com>
[ Fix bullet list indentation; add SPDX-License-Identifier. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250124182958.2040494-2-zhiw@nvidia.com
This introduces a new cgroup controller to limit the device memory.
Notable users would be DRM, dma-buf heaps, or v4l2.
This pull request is based on the series developped by Maarten
Lankhorst, Friedrich Vock, and I:
https://lore.kernel.org/all/20241204134410.1161769-1-dev@lankhorst.se/
-----BEGIN PGP SIGNATURE-----
iJUEABMJAB0WIQTkHFbLp4ejekA/qfgnX84Zoj2+dgUCZ4DhogAKCRAnX84Zoj2+
dj7bAYCnLgOut9i0JawJdrx9wzUV6fpZCt8BGnEDeE0snlKCN/7ETTOtmBqojYrR
Hwmts70BfA06NadFtMV+t6QrNOsjkk1JBPvCbSKZJK2KF7qN9Z5s8DTgw1F9rlaM
dwCAMDduRQ==
=F5bE
-----END PGP SIGNATURE-----
Merge tag 'cgroup-dmem-drm-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux into drm-next
DMEM cgroup pull request
This introduces a new cgroup controller to limit the device memory.
Notable users would be DRM, dma-buf heaps, or v4l2.
This pull request is based on the series developped by Maarten
Lankhorst, Friedrich Vock, and I:
https://lore.kernel.org/all/20241204134410.1161769-1-dev@lankhorst.se/
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Maxime Ripard <mripard@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250110-cryptic-warm-mandrill-b71f5d@houat
This code is based on the RDMA and misc cgroup initially, but now
uses page_counter. It uses the same min/low/max semantics as the memory
cgroup as a result.
There's a small mismatch as TTM uses u64, and page_counter long pages.
In practice it's not a problem. 32-bits systems don't really come with
>=4GB cards and as long as we're consistently wrong with units, it's
fine. The device page size may not be in the same units as kernel page
size, and each region might also have a different page size (VRAM vs GART
for example).
The interface is simple:
- Call dmem_cgroup_register_region()
- Use dmem_cgroup_try_charge to check if you can allocate a chunk of memory,
use dmem_cgroup__uncharge when freeing it. This may return an error code,
or -EAGAIN when the cgroup limit is reached. In that case a reference
to the limiting pool is returned.
- The limiting cs can be used as compare function for
dmem_cgroup_state_evict_valuable.
- After having evicted enough, drop reference to limiting cs with
dmem_cgroup_pool_state_put.
This API allows you to limit device resources with cgroups.
You can see the supported cards in /sys/fs/cgroup/dmem.capacity
You need to echo +dmem to cgroup.subtree_control, and then you can
partition device memory.
Co-developed-by: Friedrich Vock <friedrich.vock@gmx.de>
Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de>
Co-developed-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20241204143112.1250983-1-dev@lankhorst.se
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Dave Airlie
Bagas Sanjaya
Alexandre Courbot
Rodrigo Siqueira
Raag Jadav
Mario Limonciello
Thomas Hellström
Riana Tauro
Alyssa Rosenzweig
Alex Deucher
Charles Han
Andrew Ballance
Thomas Zimmermann
Pranav Tyagi
Maxime Ripard
Lucas De Marchi
Vignesh Raman
Anusha Srivatsa
Danilo Krummrich
Zhi Wang
Matthew Brost
Adrián Larumbe
Tomi Valkeinen
Maarten Lankhorst