This is a workaround that is still in progress, see HSD 22020521218.
If we don't have these NOPs we may see rendering corruption or even
GPU hangs.
While we still don't fully understand the issue from the hardware
point of view, let's have this workaround so we can pass CTS and move
things forward. If we need to change this later, we can. Besides, the
impact is minimal. Shaderdb/fossilize report no changes for this
patch.
On our Blackops trace, the lack of this patch causes corruption in fog
rendering (rectangles where fog was supposed to be shown don't show
the fog).
On dEQP-VK.graphicsfuzz.cov-array-copies-loops-with-limiters, without
this patch we get a GPU hang.
Backport-to: 24.2
Testcase: dEQP-VK.graphicsfuzz.cov-array-copies-loops-with-limiters
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/11813
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31331>
(cherry picked from commit 5ca883505e)
This bit is not needed for barriers and appears to trigger a
performance regression. So leave it for just for AUX-TT
flushing/invalidation.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: e3814dee1a ("anv: add plumbing/support for L3 fabric flush")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/12090
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31915>
(cherry picked from commit cb224370b6)
Detect when the temporary index buffer cannot be generated due to too
large primitive count, and simply drop the draw on the floor.
Fixes a webgl reachable asan/crash.
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/12092
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31914>
(cherry picked from commit 98ff271c5a)
This fixes a CTS hang on Hawaii.
We previously only did a CB/DB flush,
but that doesn't include a L2 cache flush.
Also fix the comment that said this is for GFX9+.
Fixes: 7c62f6fa01
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31906>
(cherry picked from commit 96b95c8427)
We may still need to insert a continue block even if there is only one
backedge, in a situation like:
for (...) {
if (...) continue;
foo();
break;
}
We want foo() to be executed before reconverging. This is important for
the BVH encoding kernel, which launches an invocation for each node in
the tree and does a preorder traversal:
while (true) {
if (!ready[node]) continue;
encode();
for (child node)
ready[child] = true;
break;
}
For the first few nodes, which will be in the same wave, we need
encode() for the root node to be called first, then its children spin
until ready, then the children call encode(), and so on. This can only
work if the children that aren't ready yet are parked while the parent
executes encode(), which requires the continue block.
This is also required because divergence analysis will assume that
uniform values written before the continue are still uniform after it,
which isn't the case now and causes an RA validation failure with Godot.
Fixes: 0fa93fb662 ("ir3: Fix convergence behavior for loops with continues")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31905>
(cherry picked from commit d3533716f9)
Computing 'htile_size/meta_size' is allowed for RADEON_SURF_MODE_1D when
RADEON_SURF_TC_COMPATIBLE_HTILE isn't set.
Lacking of computing causes performance degradation in some scenarios.
Fixes: d4d9ec55c5 ("radeonsi: implement TC-compatible HTILE")
Signed-off-by: Lu Yao <yaolu@kylinos.cn>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31617>
(cherry picked from commit 0442a6c292)
When the FS is unknown, this can happen with fast-link GPL or unlinked
ESO, rely on the number of VS/TES outputs which should be a good
approximation of the number of PS inputs.
This fixes a (huge?) performance regression from May 2023 because
for depth-only rendering, the FS is NULL and NGG culling wasn't
considered at all.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31830>
(cherry picked from commit 8e4d1965bd)
The algorithm for adding extra physical edges works by finding edges
that jump over reconvergence points. Since predicated branches don't
introduce reconvergence points, we wouldn't add a physical edge from the
true block to the false block. However, this physical edge is still
needed as control flow does fall though here. This patch fixes this by
manually adding the physical edge so that we don't need to insert a
reconvergence point for it.
Signed-off-by: Job Noorman <jnoorman@igalia.com>
Fixes: 39088571f0 ("ir3: add support for predication")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31733>
(cherry picked from commit 19c560da04)
Fix mesa_db_compact() segfaulting if compacted DB is empty. This crash
happens on writing cache entry that is bigger than DB's size limit and
when DB is empty, which can be triggered by setting DB size to a small
value.
Fixes: 32211788d0 ("util/disk_cache: Add new mesa-db cache type")
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Acked-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30988>
(cherry picked from commit 5ec424c6be)
Open one cache DB part at a time for a multi-part cache to reduce number
of FDs used by the cache. Previously multi-part DB cache instance was
consuming 100 FDs, now it's 2 and cache files are opened when cache
is read or written instead of opening them at the init time.
Fixes: fd9f7b748e ("util/mesa-db: Introduce multipart mesa-db cache")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/11776
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Acked-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30988>
(cherry picked from commit 2a9378a0f9)
Use O_CLOEXEC flag for opened cache DB files to not leak cache FDs when
process forks.
Fixes: 32211788d0 ("util/disk_cache: Add new mesa-db cache type")
Suggested-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/11810
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Acked-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30988>
(cherry picked from commit 6a2f5cb556)
flock may be interrupted by a signal, in which case it returns with
EINTR error. In this case we need to retry until it returns success
or another error.
Fixes: 32211788d0 ("util/disk_cache: Add new mesa-db cache type")
Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Acked-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/30988>
(cherry picked from commit 13c44abaac)
We shouldn't assume the bindings are sparse when we allocate an array
indexed on the binding. See, for example:
dEQP-GLES31.functional.program_interface_query.buffer_variable.random.55
Fixes: 2e833b16bc ("nir/lower_amul: Use num_ubos/ssbos instead of recomputing it.")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31611>
(cherry picked from commit 7f63fa34da)
Some nir passes, like lower_amul, expect to have varibles declared for
things that are accessed via load_ubo().
Fixes: 76e417ca59 ("turnip,ir3/a750: Implement consts loading via preamble")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31611>
(cherry picked from commit e548f90edb)
Using wayland on s390x has all the colors wrong.
Mesa reports using GBM_FORMAT_XRGB8888 but inside the buffer, the
colors are in GBM_FORMAT_BGRX8888 order.
This patch fixes it for common formats, and also introduced BGRX8888
which is the default on big endian.
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31707>
(cherry picked from commit b24d4f0c86)
__DRI_IMAGE formats are not well defined for big endian.
This patch has no functionnal change and prepare the work to better support
big endian.
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31707>
(cherry picked from commit 3814dee11a)
It's possible to enable NGG culling with ESO if shaders are linked, or
if the VS doesn't need a prolog or if TES is used. This wasn't
supposed to be enabled but I think it worked just by luck because the
user SGPR value was probably zero and NGGC was disabled at draw time.
Found by inspection.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31829>
(cherry picked from commit 62efebfd70)
This very test was working until the commit 4da147a02b
("mesa: remove fallback for GL_DEPTH_STENCIL"). Indeed this
commit lets the driver handles this path and this was
failing on evergreen r600.
The test was processed through r600_blit() which loads the
fragment shader util_make_fs_blit_zs(). This fragment shader
loads two textures the stencil and depth. The texture depth
was processed properly but the other texture was generating
incorrect values. This issue, which seems to be related to
the hardware configuration, disappears when the underlying
surface is allocated using a width multiple of 32.
This change was tested on cayman and palm with the normal test:
"piglit/bin/ext_packed_depth_stencil-getteximage -auto -fb" and
the test was modified to test all the relevant width and height
values. The gpu rv770 was not affected by this issue. Here is
the result:
spec/ext_packed_depth_stencil/getteximage: fail pass
Cc: mesa-stable
Signed-off-by: Patrick Lerda <patrick9876@free.fr>
Acked-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31757>
(cherry picked from commit d19e2597ce)
We don't dirty the CS state, so if a 3D blit comes between binding a
compute pipeline and executing a dispatch then we won't re-emit the
pipeline and invalidating CS state causes immediates emitted via
CP_LOAD_STATE to disappear. Fixes
dEQP-VK.binding_model.descriptor_buffer.ycbcr_sampler.compute_comp.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31764>
(cherry picked from commit 048afdd438)
This GPU seems to have half the compute constlen of other a7xx GPUs,
because there are sporadic hangs in dEQP-VK.robustness.robustness2.* and
other tests unless we limit the constlen. This does *not* happen on
SM8550-HDK, so it does seem to be specific to the GPU in x1e laptops.
Fixes: b0d22461b9 ("freedreno: Enable the X1-85")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31764>
(cherry picked from commit 3c8190e8b2)
panvk provides driver UUID generated from build id of the dynamic
library, but ld_args_build_id isn't used during linking. This leads to
broken drivers when building mesa with a toolchain defaults to
--no-build-id. Let's specify the flag explicitly.
Fixes: 8ea2931ed1 ("panvk: Generate proper device and driver UUIDs")
Signed-off-by: Yao Zi <ziyao@disroot.org>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31654>
(cherry picked from commit 5ffc5ba8ef)
It was based on misunderstanding of how holes are sorted, they are
sorted by address and not by size.
Fixes: df3ba95a24
("util/vma: Add function to get max continuous free size")
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31722>
(cherry picked from commit 3209a97c5c)
When only of the depth/stencil aspects is used, RADV dispatches a
compute shader to initialize the HTILE buffer. But dispatching on SDMA
just hangs and the only way to initialize the HTILE buffer is to clear
both aspects using a memory fill operation.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31803>
(cherry picked from commit be81c8b8db)
If the stencil clear value was larger than the maximum supported by the hardware
(255) then it would end up corrupting other fields in TA_STATE_ISPA. The Vulkan
1.0.266 spec says for VkClearDepthStencilValue:
"stencil is the clear value for the stencil aspect of the depth/stencil
attachment. It is a 32-bit integer value which is converted to the
attachment’s format by taking the appropriate number of LSBs."
As such, mask the clear value when packing TA_STATE_ISPA.
Fixes a number of GLES tests, including:
dEQP-GLES2.functional.depth_stencil_clear.*stencil_scissored*
dEQP-GLES2.functional.fragment_ops.stencil.*
dEQP-GLES3.functional.depth_stencil_clear.*stencil_scissored*
dEQP-GLES3.functional.fragment_ops.stencil.*
Fixes: 821c6b9342 ("pvr: Implement depth/stencil/depth+stencil attachment...")
Signed-off-by: Frank Binns <frank.binns@imgtec.com>
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31679>
(cherry picked from commit 1612255de6)
