The round-to-nearest-even implementation found in lower_2f() is incorrect
for any value having a significand that is not directly representable
and whose non-representable part lies between 1 and half the minimum
representable value. In this case, the significand is rounded up instead
of being rounded down.
Fixes: 936c58c8fc ("nir: Extend nir_lower_int64() to support i2f/f2i lowering")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Tested-by: Jesse Natalie <jenatali@microsoft.com>
Acked-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6290>
(cherry picked from commit 199bea0fd8)
Don't have the shader do a 32-bit unorn to float conversion,
the values don't remain accurate then.
Fixes:
GTF-GL45.gtf30.GL3Tests.framebuffer_blit.framebuffer_blit_functionality_multisampled_to_singlesampled_blit
for 32-bit unorm depth buffers.
Cc: "20.2" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6044>
(cherry picked from commit 2e40b2c155)
It isn't clear to me why, but this breaks in some cases (such as some
dEQP cases where the blob does a translate too).
This reverts commit 9f2997dad0.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Cc: mesa-stable
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6326>
(cherry picked from commit e03622e50f)
Having a single init function works as expected for shared llvm, but
when using a static llvm only one llvm will get initialized.
This commit introduces 2 separate init function:
- shared llvm = single public init function
- static llvm = one init function for each module using llvm
Fixes: 50d20dc055 ("ac/llvm: export ac_init_llvm_once in targets")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3376
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6253>
(cherry picked from commit b7c04b1790)
KHR-GL45.robust_buffer_access_behavior.vertex_buffer_objects
on the CTS 4.6.0 branch and this fixes it.
Roland identified that if the vertex format doesn't contain channels
then we shouldn't be overriding them to 0, so RGB fetch out of bounds
should return 0 for RGB, but the A channel should still be getting back
1.
Cc: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6287>
(cherry picked from commit 430e3310e2)
This is a left over from the earlier version of
VK_KHR_performance_query where we used kernel relocs to implement
multi passe queries.
We're using self modifying batches now so we shouldn't need any
relocation.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 2001a80d4a ("anv: Implement VK_KHR_performance_query")
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6291>
(cherry picked from commit 031f9e17d2)
When importing a DMA-BUF, the image layout created in vkImageCreate may
not match the imported BO's. To make this work we redo the layout based
on the metadata of the imported image.
The original patch did a delayed allocation just as for AHB, but that
does not work for images that are not imported (but e.g. exported only).
Original patch by Simon Ser <contact@emersion.fr>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2801
CC: mesa-stable
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6274>
(cherry picked from commit d19bc94e4e)
Calling SET_TILING on a DMA buffer with the gen12 CCS modifier can fail
unnecessarily. The main surface in the BO is Y-tiled, but the CCS portion is
linear and can have a stride that's not a multiple of 128B. Because SET_TILING
is called on the CCS plane with I915_TILING_Y, the ioctl will sometimes reject
the stride.
SET_TILING was originally used in b6d45e7f74 to
fix an assertion failure in iris_resource_from_handle. Assigning the BO's
tiling_mode field is sufficient to avoid the failure.
Fixes: c19492bcdb ("iris: Handle importing aux-enabled surfaces on TGL")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6296>
(cherry picked from commit c111e9099c)
This change fixes off-by-one results in corner cases such as
0xffffffff / 0x11111111. For details refer to LLVM bug 46212.
Fixes: 8b98d0954e ('nir/lower_idiv: add new llvm-based path')
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6281>
(cherry picked from commit 8277334f39)
inputs_read/outputs_written are used for a shader stage to
determine the layout of input and output storage. Adjacent stages must
agree on the layout, so adjacent input/output bitfields must match.
Most of the time, cross-stage optimizations make that happen anyway,
but there are some cases (with special values like clip distances and
point size) where this doesn't happen.
Fixes crashes in dEQP-VK.subgroups.*.framebuffer.*_tess_eval
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3210
Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6102>
(cherry picked from commit 2701f887fc)
This was just missing.
Fixes: 57e796a12a ("radv: Implement VK_EXT_custom_border_color")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: John Galt <johngaltfirstrun@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6276>
(cherry picked from commit 638a09b827)
Fix warnings reported by Coverity Scan.
Resource leak (RESOURCE_LEAK)
leaked_storage: Variable bt1 going out of scope leaks the storage
it points to.
leaked_storage: Variable bt2 going out of scope leaks the storage
it points to.
Fixes: d0d14f3f64 ("util: Add unit test for stack backtrace caputure")
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6246>
(cherry picked from commit 96cfc684e6)
Port the change done for RGBX8888 in
02a1f95386.
If XR24 images are considered to be VIEW_CLASS_24_BITS-compatible, it's
reasonable to assume that XB24 images would be as well.
Fixes: bf576772ab ("dri_util: add driImageFormatToSizedInternalGLFormat function")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6095>
(cherry picked from commit 8abf59ff98)
It could happen that only the branch condition was computed in WQM
and not the branch instruction.
There is now some rendundancy which should be cleaned up.
Fixes: 3817fa7a4d ('aco: fix WQM handling in nested loops')
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6260>
(cherry picked from commit fdb97d3d29)
Fixes random failures of dEQP-VK.image.qualifiers.volatile.cube_array.r32i
and similar tests on Vega.
fossil-db (Navi):
Totals from 6 (0.00% of 135946) affected shaders:
VMEM: 1218 -> 1110 (-8.87%); split: +2.46%, -11.33%
SMEM: 174 -> 189 (+8.62%)
Copies: 84 -> 87 (+3.57%)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: cd392a10d0 ('radv/aco,aco: use scoped barriers')
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6174>
(cherry picked from commit 7b4c24eb67)
Found by inspection, doesn't fix anything known.
Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6279>
(cherry picked from commit e4c6204d65)
MSAA worked before etnaviv landed in upstream mesa but got
broken over time. Disable MSAA completely until it is fixed again.
Fixes problems/crashes with applications that want to make use of MSAA.
Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5608>
(cherry picked from commit 044b238507)
The fixes tag isn't so much because it was incorrect before, but because
I'm going to send a kernel patch to fix the typo, and that will break
old crashdec.
Fixes: 1ea4ef0d3b ("freedreno: slurp in decode tools")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6242>
(cherry picked from commit cbfce486f2)
We cannot decompress from the compute queue. While I'm pretty sure
VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL is only useful on the
graphics queue, I cannot find a VU that prevents the transition
from happening on another queue, so we need to be careful here.
This patch ensures we do the decompression on the barrier that changes
the queue ownership.
Another problem was that DCC images were considered fast-clearable
when not DCC compressed, which resulted in a mess with concurrent
queue ownership.
Cc: <mesa-stable@lists.freedesktop.org>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3387
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6252>
(cherry picked from commit e362ccb20c)
Currently Linux kernel gathers performance counters at fixed
intervals (~5-10ms), so if application uses AMD_performance_monitor
extension and immediately after glFinish() asks GL driver for HW
performance counter values it might not get any data (values == 0).
Fix this by moving the "read counters from kernel" code from
"is query ready" to "get counter values" callback with a loop around
it. Unfortunately it means that the "read counters from kernel"
code can spin for up to 10ms.
Ideally kernel should gather performance counters whenever we ask
it for counter values, but for now we have deal with what we have.
Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com>
Cc: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5788>
(cherry picked from commit 2fbab5a1b3)
https://github.com/KhronosGroup/EGL-Registry/pull/95 has moved
a couple of extensions defines and functions to the upstream `eglext.h`,
but when 9a74746bd1 sync'ed these files we broke compilation
of apps that require these symbols on systems that don't have the
updated Khronos headers.
On non-GLVND builds, we still provide these headers, so everything's
fine, but on GLVND builds the Khronos headers are external so we need to
make sure we have a libglvnd version that's recent enough.
Fixes: 9a74746bd1 ("EGL: sync headers with Khronos")
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Acked-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6069>
(cherry picked from commit dd003abd2f)
The option is not a toggle to "allow GPU vendor to be overridden", it
*is* the override.
Fixes: dca119f12c ("mesa/gallium: add dric option to allow overriding GL vendor string")
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6207>
(cherry picked from commit 7fbadfc385)
Freedreno needs at least Lua 5.2, but the current code will report found
for 5.1, which doesn't actually work.
Fixes: caa107cb8d
("freedreno/decode: move dependencies up a level")
Reviewed-by: Rob Clark <robclark@freedesktop.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6229>
(cherry picked from commit 1e28745bc0)
The LDS size can't overflow anymore, so we can use the correct max LDS size.
Fixes: a23802bcb9 - ac,radeonsi: start adding support for gfx10.3
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
(cherry picked from commit e2e700f605)
The code applied the restriction too late, which could overflow LDS size,
which started happening more often after the minimum vertex count was
increased for Sienna.
Incorporate the clamping into the previous code for rounding up the counts.
Now the LDS size can never overflow, but it may use vector lanes less
efficiently (max_gsprims can be decreased more), which will be addressed
in the next commit.
Fixes: 4ecc39e1aa ("radeonsi/gfx10: NGG geometry shader PM4 and upload")
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
(cherry picked from commit 64c741ffb7)
This reverts commit c4b5fd9ab0.
It breaks mipmapping. This is only meant to be used by OpenCL, which allows
setting a user pitch for linear images. In all other cases, don't support
a custom pitch.
Fixes: c4b5fd9ab0 "radeonsi: honor a user-specified pitch on gfx10.3"
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6137>
(cherry picked from commit 61c671c97e)
