Huge thanks to Tapani Pälli for debugging this issue, figuring out
what was going wrong, proposing fixes, and walking me through where
things were going off the rails.
BLORP always disables tessellation and geometry shaders. Our handling
tried to look at ice->shaders.uncompiled[] to determine whether the next
draw needed those shaders. If not, we can leave BLORP's residual state
that disabled those stages in place, and skip looking at it.
Unfortunately, predicting the future is a bit fraught, in part due to
the uncompiled[] and prog[] arrays being slightly out of sync at times.
Consider the following case:
1. Draw with tessellation shaders in place
=> uncompiled[TES] and prog[TES] will both point at valid shaders.
2. Gallium calls pipe->bind_tes_state(NULL).
=> This makes uncompiled[TES] point at NULL, and flags
IRIS_STAGE_DIRTY_UNCOMPILED_TES.
Because iris_update_compiled_shaders() hasn't happened yet,
uncompiled[TES] is NULL but prog[TES] has the stale TES from
the previous draw still.
3. BLORP operations happen
=> BLORP sees uncompiled[TES] == NULL and decides that tessellation
is off for the upcoming draws. So it skips flagging tess state.
4. Gallium calls pipe->bind_tes_state(shader from step #1).
=> uncompiled[TES] points at the original shader.
IRIS_STAGE_DIRTY_UNCOMPILED_TES gets flagged again.
5. Draw again
=> This calls iris_update_compiled_shaders(), which sees that
a TES is bound, and calls iris_update_compiled_tes(). But
because the same shader was bound as before, the program it
comes up with is identical to the one already bound at
ice->shaders.prog[TES]. So, it thinks it doesn't have to
flag any tessellation state dirty because it was already
set up for the last draw.
This random unbind and rebind between draws leads to a situation
where, at step #3, BLORP thinks it can skip flagging tessellation
state (nothing is bound), and at step #5, normal state handling
thinks it can skip flagging tessellation state (nothing changed
since last time). So nobody does, and things break.
This unbind appears to be happening when st_release_variants()
decides it wants to free some shaders. Then a rebind happens to
put back the actual shader for the draw. So, it's not theoretical.
To fix this, we change BLORP to look at ice->shaders.prog[] rather
than uncompiled[]. This is equivalent to thinking about the previous
draw, rather than the next. If the last draw had tessellation off,
then BLORP's disabling was a no-op, and the GPU is still in the same
state as the previous draw. This is more reliable than predicting
the future.
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8308
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9678
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24880>
(cherry picked from commit d693027a00)
The msm driver reserves the actual DMABUF size in the memory map, while
TU can request smaller memory chunk to be allocated. This potentially
can lead to a situation when next allocation IOVA will be in the middle
of the address space which is reserved for the DMABUF. Pass the
`real_size' to TU allocator instead, so that kernel and userspace have
the same picture of memory allocations.
Cc: mesa-stable
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24861>
(cherry picked from commit 2fdcc00b01)
At the time this was added to fix some test failures. But it seems that
the failures were happening due to missing cache flushes, so
this extra space is no longer neccessary.
Fixes: 37b4eacc ("intel/isl: Resize clear color buffer to full cacheline")
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24768>
(cherry picked from commit caa5c23e48)
EXT extension was added without tests so these functions did
not work properly.
Fixes: 799710be88 ("mesa: Add EXT_texture_mirror_clamp_to_edge to extension table")
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24845>
(cherry picked from commit d65fe6eff1)
The vulkan spec says all conversions are correctly rounded, so if the input
is larger than the largest fp16 value, we need to return MAX_FLOAT/inf
instead of cutting off the msbs.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24826>
(cherry picked from commit 6d949e18fd)
Same as the other bpermute pseudo instructions.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24693>
(cherry picked from commit 85957dd6e5)
The blob replicates both the value mask as well as the stencil reference
of the back-facing stencil to the front-facing stencil. This fixes the
remaining failures in the following dEQPs:
dEQP-GLES2.functional.fbo.render.*_stencil_index8
Fixes: c8ccd63911 ("etnaviv: Fix depth stencil ops on GC880/GC2000")
Signed-off-by: Marek Vasut <marex@denx.de>
Acked-by: Lucas Stach <l.stach@pengutronix.de>
Acked-by: Christian Gmeiner <cgmeiner@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4867>
(cherry picked from commit ef4cb2431d)
For z surfaces, flags.texture should be based on
RADEON_SURF_TC_COMPATIBLE_HTILE alone. Otherwise, addrlib could pick a
_X/_T swizzle mode for a MSAA depth texture, which is said to be broken:
When _X/_T swizzle mode was used for MSAA depth texture, TC will get zplane
equation from wrong address within memory range a tile covered and use the
garbage data for compressed Z reading which finally leads to corruption.
Fixes: de0885cdb8 ("amd/surface: add RADEON_SURF_NO_TEXTURE flag")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24767>
(cherry picked from commit e74c3dbb70)
And use the type in functions instead of a generic `uint32_t` to make it
easier to notice the wrong type.
Fixes: 47e02a2ef1 ("v3dv: add a fast path for vkCmdClearAttachments")
Signed-off-by: Eric Engestrom <eric@igalia.com>
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24787>
(cherry picked from commit ae0cb0b998)
Triangle strips with adjacency have 6 vertices input, so we need an array big
enough for all 6 vertices to avoid overflow. Fixes passthrough GS generated for
KHR-GLES31.core.draw_indirect.basic-mode-*-triangle*adj*.
Fixes: ea14579f3d ("nir: handle primitives with adjacency")
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24780>
(cherry picked from commit 558e36f641)
`ds->db.format` is a `pipe_format`, while `buffer_infos[handle].format` is
a `VkFormat`; the conversion from one to the other was missing.
Fixes: 99ba529fee ("zink: implement descriptor buffer handling of bindless texture")
Signed-off-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24790>
(cherry picked from commit ab0f0d1563)
It does not preserve everything. It adds and removes instructions and
even adds a variable.
Fixes: f17b41ab4f ("nir: add lowering pass for helperInvocationEXT()")
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24760>
(cherry picked from commit 831085afa3)
I have no idea why a bigger size doesn't work, the hardware doesn't
complain, but it turns out that uploading big shaders still causes issues
with the old limit. *shrug*
Fixes: 7f63d2ebdb ("nv50: fix code uploads bigger than 0x10000 bytes")
Signed-off-by: Karol Herbst <git@karolherbst.de>
Reviewed-by: M Henning <drawoc@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24758>
(cherry picked from commit 3e0cd6dfb9)
It uses a poll function that waits for a second hoping for another thread
to catch up, which is not a reliable way to do synchronization. The test
has been spuriously failing merges on a regular basis recently.
This is issue #9222, which I'm leaving open until the author can fix the test.
Fixes: 3b69b67545 ("util/fossilize_db: add runtime RO foz db loading via FOZ_DBS_DYNAMIC_LIST")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24755>
(cherry picked from commit 4dfd306454)
This is required to get rid of unneeded memory operations, like direct
scratch stores/loads to the same location.
Fixes: 66c6061491 ("rusticl/kernel: get rid of initial function_temp type lowering")
Signed-off-by: Karol Herbst <git@karolherbst.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24734>
(cherry picked from commit cc2f59d840)
VkPipelineColorBlendStateCreateInfo::attachmentCount cannot be used to
generate the CWE mask since it cannot be read if enough dynamic state is in use
instead just pass the max mask and let drivers figure it out
cc: mesa-stable
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24673>
(cherry picked from commit 0fb9064231)
It's unnecessary because earlier parts of the pass will ensure that a
mov of undef is turned into an undef. It's also wrong because
nir_op_mov has different semantics from nir_op_vecN when it comes to how
sources map to destination components.
Fixes: 5f26c21e62 ("nir: Expand opt_undef to handle undef channels in a store intrinsic")
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24704>
(cherry picked from commit 408929289a)
For mov we need to follow the swizzle for the destination component, not
grab swizzle[0] for some random source.
Fixes: a406fff78a ("nir/inline_uniforms: support vector uniform")
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24704>
(cherry picked from commit 9bcc9597a5)
These work in some circumstances (dEQP-VK.spirv_assembly.instruction.graphics.16bit_storage.input_output_float_16_to_64.scalar9_tessc),
but I'm not sure if they work in all, blending certainly doesn't work and
this probably wasn't intended in the first place.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Fixes: 01bd012edd ("amd: fix 64-bit integer color image clears")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24400>
(cherry picked from commit 405f3bf990)
This reverts commit 6b494745be.
The logic is not entirely correct: the comparison is between two
static-analysis estimates of a dynamic system with variables that aren't
captured by the shader source, so using ">" will always have greater potential
to cause regressions whenever the performance difference between the two builds
is something not captured by the static model, no matter how much the model is
improved.
Reference: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9262
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24615>
(cherry picked from commit d142c845d0)
