This adds a generic lowering pass for coop mat flexible dimensions.
This should be suitable for all drivers that implement coop mat2 flexible dimensions
or even just lowering sw exposed sizes to hw sizes.
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36544>
We're supposed to completely ignore VkTimelineSemaphoreSubmitInfo if
there aren't any timeline semaphores, including the array lengths, which
is made clear by the various VUs already cited by the code. The
vkQueueSubmit() path correctly handled this when asserting but still
dereferenced pWaitSemaphoreValues unconditionally, which could lead to
dereferencing an invalid pointer if waitSemaphoreValueCount is less than
waitSemaphoreCount. The vkQueueSparseBind() path didn't even assert
correctly. Bring vkQueueSparseBind() in line with vkQueueSubmit()
and make both only dereference the wait/signal array once we've
determined it must be present. While we're here, also fix the assert in
vkQueueSubmit() to disallow a waitSemaphoreValueCount of 0 if there are
timeline semaphores present, which conversely is not allowed.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36989>
We are reading out some of the parameters from IR data structure those
have been written previously, on some platforms L3 is not coherent, so
explicitly add those flushes.
Cc: mesa-stable
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36952>
The blit code is destructive on the framebuffer state, which means
that it can set new render targets. If you have 2 BGRA surfaces bound
for logic ops, then after setting up the surface for the first one,
the blit for the second will end up destroying + re-creating the
surface for the first one.
Let's be robust to this by putting the blit in a first pass, and
then actually initializing all of the descriptors in a second pass.
This is still woefully inefficient but at least it's correct.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36945>
Enable cross-building nvk and panvk for Android to make it easier to
spot build regressions.
NOTE: nvk is built only for x86_64, and panvk is built only for aarch64.
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36710>
Handle dep_libdrm before the driver specific libdrm modules, this is for
when libdrm is built as a subproject, for example libdrm_amdgpu is only
available after dep_libdrm has been added.
Acked-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36710>
Fix the rule about not ignoring files under subprojects/packagefiles/
which is not covering files in subdirectories of
subprojects/packagefiles
Acked-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36710>
Add a comment about updating tags in .gitlab-ci/image-tags.yml to the
.gitlab-ci/container/create-android-cross-file.sh as it is not immediate
that it gets called from .gitlab-ci/container/debian/android_build.sh
which also requires to update DEBIAN_BUILD_TAG.
Reviewed-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36710>
Add rust compiler definitions to the create-android-cross-file.sh file
to be able to cross-build drivers that use Rust code.
This is inspired by the changes in commit 2f5db959a7 ("docs/android:
update cross file and add nvk instructions", 2025-08-01)
Also add rust and bindgen to the debian/android_build container.
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36710>
This avoids having to hardcode the proxy in the traces `download-url` or
jobs setting `PIGLIT_REPLAY_EXTRA_ARGS` and accidentally overriding the
default args when the author meant to append.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36955>
FDO_HTTP_CACHE_URI is not defined, but LAVA_HTTP_CACHE_URI is and is the
right URL for this.
This job is currently disabled, but fix it in preparation for when
someone eventually brings it back.
Note that this line also has another bug that will be addressed by the
next commit.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36955>
Without this, I get failures in the following CTS test:
dEQP-VK.api.device_init.create_instance_device_intentional_alloc_fail.basic
Fixes: 05006c21dd ("panvk/utrace: Alloc utrace copy buf from userspace heap")
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36980>
There is a FW issue when using constrained intra prediction with rate
control enabled, causing unexpected quality degradation.
Disable it until FW fix is available.
Cc: mesa-stable
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36837>
RADV_DYNAMIC_RASTERIZATION_SAMPLES triggers the following states:
- FS (not needed when FS is NULL)
- MSAA (already triggered)
- BINNING (use radv_get_ps_iter_samples() on GFX9)
- OCCLUSION_QUERY (doesn't use the PS)
- DB_SHADER_CONTROL (already triggered)
- RAST_SAMPLES (use radv_get_ps_iter_samples())
- NGGC (doesn't use the PS)
So this can be simplified to BINNING (gfx9) | RAST_SAMPLES.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36912>
This reduces the number of states that are re-emitted but the logic
is mostly duplicated because sample shading can be set from the
fragment shader or the graphics pipeline. Could be refactored
eventually.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36912>
This is already handled slightly above in the same function. Also
state->dirty isn't for RADV_DYNAMIC_xxx and there is no corresponding
RADV_CMD_DIRTY_xxx either.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36912>
Right now, we store the last VkDeviceMemory object bound to an image in
panvk_image::mem, but this doesn't work for disjoint images where the mem
object can differ on each plane.
Move panvk_image::mem to panvk_image_plane::mem and prefix the offset
field with mem_, so it's clear the offset refers to the mem object.
Note this should only fix host copy on disjoint images, since the GPU
address was already properly set at bind time.
Fixes: 1cd61ee948 ("panvk: implement VK_EXT_host_image_copy for linear color images")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Olivia Lee <olivia.lee@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36926>
libbacktrace compatibility has been dropped since Android 14, so the
current flags and deps shall be kept behind api level < 34.
Meanwhile, its successor, libunwindstack, has been available since
Android 11 (api level 31). So one can hook that up if needed.
Reviewed-by: Antonio Ospite <antonio.ospite@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36961>
