Chia-I Wu [Mon, 13 Mar 2023 21:35:55 +0000 (14:35 -0700)]
amd/drm-shim: add amdgpu drm-shim
This is enough to run offscreen apps such as vulkaninfo or deqp-vk.
v2: remove unnecessary idep_amdgfxregs_h dependency
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21892>
Chia-I Wu [Wed, 10 May 2023 18:27:42 +0000 (11:27 -0700)]
drm-shim: apply file overrides for open
loader_get_pci_driver calls os_read_file on linux to get the pci id, and
os_read_file uses open instead of fopen.
This allows loader_get_pci_driver to work rather than falling back to
loader_get_kernel_driver_name.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22951>
Jesse Natalie [Tue, 9 May 2023 21:57:08 +0000 (14:57 -0700)]
microsoft/compiler: Do basic I/O analysis for dependency tables
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22949>
Jesse Natalie [Mon, 8 May 2023 21:40:47 +0000 (14:40 -0700)]
microsoft/compiler: Allocate space for I/O and viewID dependency tables before instruction processing
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22949>
Danylo Piliaiev [Thu, 25 Aug 2022 15:25:30 +0000 (18:25 +0300)]
tu: Re-enable bufferDeviceAddressCaptureReplay
We cannot immidiately free VMA range when BO is freed, we have to
wait until kernel stops considered BO as busy and frees its internal
VMA range. Otherwise userspace and kernel VMA will get desynchronized.
To fix this and re-enable replaying of BDA we place BO's information
into a queue. The queue is drained:
- On BO allocation;
- When we cannot allocate an iova passed from the client.
For more information about this see:
https://gitlab.freedesktop.org/mesa/mesa/-/issues/7106
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18254>
Rob Clark [Wed, 10 May 2023 17:42:17 +0000 (10:42 -0700)]
tu: Move queue deletion to last
For zombie vma tracking, we'll need access to the queue at bo deletion
time. This simplest way to make that work is just move queue deletion
to late in device teardown.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18254>
Danylo Piliaiev [Tue, 11 Oct 2022 15:51:08 +0000 (17:51 +0200)]
tu: Move VMA heap to the logical device
Since last commit drm fd is being created on per logical device
granularity, which means each logical device has its own
address space. So VMA heap could be moved to logical device.
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18254>
Danylo Piliaiev [Tue, 11 Oct 2022 13:43:31 +0000 (15:43 +0200)]
tu: Create drm fd per logical device
The main reason is to simplify BO managment when
bufferDeviceAddressCaptureReplay would be enabled.
Having to track some BO information in physical device and some
info in logical device gets challenging when BOs are shared
between logical devices.
Other benefits:
- Isolation from hangs in other logical devices;
- Each logical device limited only by its own address space size.
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18254>
Emma Anholt [Wed, 10 May 2023 18:24:59 +0000 (11:24 -0700)]
ci/zink+anv: Skip a couple more long tests pre-merge.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22866>
Emma Anholt [Mon, 8 May 2023 19:51:31 +0000 (12:51 -0700)]
ci: Re-enable some piglit tests that should be fast enough post-uprev.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22866>
Collabora's Gfx CI Team [Sat, 6 May 2023 00:04:20 +0000 (00:04 +0000)]
Uprev Piglit to
536975d94a40cf76a69fcfa786c2513eccd0c989
https://gitlab.freedesktop.org/mesa/piglit/-/compare/
79a084c56b6dd79f7c3a97b57a72963121ebb1e6...
536975d94a40cf76a69fcfa786c2513eccd0c989
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22866>
Emma Anholt [Mon, 8 May 2023 23:37:09 +0000 (16:37 -0700)]
zink: Don't flag legacy_shadow_mask for RED-only reads in the shader.
It is very common in games to read just the .x channel of a vec4 shadow
result (since GL defaults to either LUMINANCE or RED depth mode depending
on context). So, we can avoid shader recompiles to handle the other
components, in that case.
Fixes some recompiles in CS:GO.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22912>
Emma Anholt [Mon, 8 May 2023 22:31:19 +0000 (15:31 -0700)]
zink: Fix silly void * type in rewrite_tex_dest.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22912>
Emma Anholt [Mon, 8 May 2023 23:12:42 +0000 (16:12 -0700)]
zink: Explain some of the current pathway for shadow sampling.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22912>
Emma Anholt [Tue, 9 May 2023 19:40:23 +0000 (12:40 -0700)]
mesa: Fix precompile of GLSL programs with shadow samplers.
Reduces fp variant recompiles on google's CS:GO trace on zink+anv from 115
to 31.
Fixes:
0843d4cbc354 ("nir: switch to a normal sampler for ARB program with not depth textures")
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22928>
Emma Anholt [Tue, 9 May 2023 19:21:35 +0000 (12:21 -0700)]
mesa: Fix debug logging of fp compile compare func.
When we're doing COMPARE_FUNC_ALWAYS, that's not part of a shader
precompile miss.
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22928>
Jiadong Zhu [Sat, 6 May 2023 09:35:05 +0000 (17:35 +0800)]
ac: enable SHADOW_GLOBAL_CONFIG for preemptible ib
SHADOW_GLOBAL_CONFIG is mandatory for mid command buffer preemmption.
Fixes:
69014d8c94f (radeonsi: implement CP register shadowing)
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22916>
Konstantin Seurer [Sun, 7 May 2023 09:53:21 +0000 (11:53 +0200)]
nir/lower_io: Emit less iadd(x, 0)
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22890>
Rob Clark [Sun, 7 May 2023 15:17:05 +0000 (08:17 -0700)]
freedreno/a5xx+a6xx: Don't allocate LRZ for z32
We don't do LRZ in this case, so no point in allocating the LRZ buffer.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sun, 23 Apr 2023 17:48:41 +0000 (10:48 -0700)]
freedreno/a6xx: Actually use LRZ for ms
We know the z value after the fallback clear. But we need to set
rsc->lrz_valid _after_ the fallback clear invalidates it.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sun, 23 Apr 2023 14:21:33 +0000 (07:21 -0700)]
freedreno/a6xx: Move LRZ clears to gmem
If we have multiple LRZ clears, emit them all at once. This also avoids
redundant LRZ clears if app does multiple clears in sequence.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sat, 22 Apr 2023 20:06:15 +0000 (13:06 -0700)]
freedreno/a6xx: New subpass on mid-frame clears
If we get a mid-frame clear, split out a new subpass rather than having
to fall-back to u_blitter clears.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sat, 22 Apr 2023 19:44:59 +0000 (12:44 -0700)]
freedreno/a6xx: Per-subpass LRZ
Allow the LRZ buffer to be re-allocated if a mid-frame depth clear
starts a new subpass.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sat, 22 Apr 2023 18:00:05 +0000 (11:00 -0700)]
freedreno/a6xx: Introduce batch subpasses
Just the scaffolding for now, nothing actually creates multiple sub-
passes yet. For now, only planning to use this for a6xx, as other
gens are doing clears on 3d.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sat, 22 Apr 2023 17:36:36 +0000 (10:36 -0700)]
freedreno/a6xx: Split tile loads and clears
This will give better visibility in perfetto, and prepares for the next
commit where we could have per-subpass clears.
While we are at it, start adopting vulkan terms for tile load/store. No
need to be pointlessly different.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sat, 22 Apr 2023 18:07:58 +0000 (11:07 -0700)]
freedreno/a6xx: Switch to batch->cleared
batch->fast_cleared will be per-subpass. But we can use the cleared
bitmask instead in the few places where we just need to know if there
was a clear in any subpass. For the conditional-ib it is even
preferable since we know a clear touched the contents of the tile so
we know what the result of the conditional would be.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sat, 22 Apr 2023 16:55:57 +0000 (09:55 -0700)]
freedreno/a6xx: Simplify per-tile conditional IBs
Handle the logic which decides between conditional or unconditional IB
in one place.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Wed, 19 Apr 2023 22:21:11 +0000 (15:21 -0700)]
freedreno/a6xx: Add ctx->emit_sysmem()
Once we introduce subpass, it won't be just a single IB. But per
subpass clears + IB. So interoduce a sysmem counterpart for
emit_tile().
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Wed, 19 Apr 2023 16:33:06 +0000 (09:33 -0700)]
freedreno/a6xx: Move LRZ clear to blitter
This is where it belongs. And will simplify moving LRZ clears to
fd6_gmem.cc
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Rob Clark [Sat, 22 Apr 2023 19:32:21 +0000 (12:32 -0700)]
freedreno/batch: Add helper to set fb state
Stop open-coding and add a helper.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22895>
Mike Blumenkrantz [Wed, 10 May 2023 14:49:14 +0000 (10:49 -0400)]
zink: disable always zs feedback loop on radv
this shouldn't have been enabled
Fixes:
56fb2580642 ("zink: replace mixed_zs with zs feedback loops")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22946>
Yiwei Zhang [Wed, 10 May 2023 05:38:58 +0000 (05:38 +0000)]
anv: apply ANV_BO_ALLOC_IMPLICIT_SYNC for external memory
This is necessary to make anv work with clients like VA-API which relies
on implicit fencing only. The bahavior matches iris i915_batch_submit.
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22937>
Eric Engestrom [Wed, 10 May 2023 10:16:49 +0000 (11:16 +0100)]
ci: bump bin/ci/ deps to support python 3.11
Signed-off-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22943>
Luigi Santivetti [Mon, 3 Apr 2023 09:02:02 +0000 (10:02 +0100)]
pvr: add GUARD_SIZE_DEFAULT for CDM and VDM control stream links 1 and 2
Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Reviewed-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22631>
Luigi Santivetti [Thu, 20 Apr 2023 10:46:03 +0000 (11:46 +0100)]
pvr: use PVR_DW_TO_BYTES for stream_link_space calculation
Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Reviewed-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22631>
Timur Kristóf [Sat, 6 May 2023 16:00:00 +0000 (18:00 +0200)]
aco: Initialize vcmpx field in get_cmp_info.
Fixes:
578d0a19341a5df2be555e19396a20c81d79c7a9
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22885>
Timur Kristóf [Sat, 6 May 2023 15:03:22 +0000 (17:03 +0200)]
aco: Don't allow any VALU instruction to write m0.
Fixes:
d5398b62da1913e7224c826da0dbd5fa88436f18
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22885>
Simon Ser [Thu, 8 Dec 2022 16:14:02 +0000 (17:14 +0100)]
vulkan/wsi/wayland: add 16-bit formats
Signed-off-by: Simon Ser <contact@emersion.fr>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20234>
Iago Toral Quiroga [Thu, 4 May 2023 11:23:28 +0000 (13:23 +0200)]
broadcom/compiler: increase peephole limit to 24 instructions
This helps by reducing the number of branches with their corresponding
delay slots, at the expense of additional register pressure. It also helps
a lot with SFU stalls, probably because removing control-flow blocks
gives us more QPU scheduling flexibility to hide them.
Shader-db results below correspond to the "closed shaders" set, since the
full set is very dominated by the massive impact this change has on Skia's
shaders (for the better), so this is probably more representative of real
impact:
total instructions in shared programs:
11887255 ->
11854898 (-0.27%)
instructions in affected programs: 538170 -> 505813 (-6.01%)
helped: 1653
HURT: 43
Instructions are helped.
total threads in shared programs: 385924 -> 385872 (-0.01%)
threads in affected programs: 236 -> 184 (-22.03%)
helped: 22
HURT: 48
Inconclusive result (%-change mean confidence interval includes 0).
total uniforms in shared programs: 3552808 -> 3547894 (-0.14%)
uniforms in affected programs: 157486 -> 152572 (-3.12%)
helped: 1673
HURT: 35
Uniforms are helped.
total max-temps in shared programs: 2062403 -> 2064720 (0.11%)
max-temps in affected programs: 18209 -> 20526 (12.72%)
helped: 168
HURT: 369
Max-temps are HURT.
total spills in shared programs: 1937 -> 1994 (2.94%)
spills in affected programs: 79 -> 136 (72.15%)
helped: 0
HURT: 1
total fills in shared programs: 2652 -> 2717 (2.45%)
fills in affected programs: 115 -> 180 (56.52%)
helped: 0
HURT: 1
total sfu-stalls in shared programs: 19349 -> 18010 (-6.92%)
sfu-stalls in affected programs: 2321 -> 982 (-57.69%)
helped: 674
HURT: 74
Sfu-stalls are helped.
total inst-and-stalls in shared programs:
11906604 ->
11872908 (-0.28%)
inst-and-stalls in affected programs: 541339 -> 507643 (-6.22%)
helped: 1656
HURT: 43
Inst-and-stalls are helped.
total nops in shared programs: 245740 -> 238085 (-3.12%)
nops in affected programs: 19282 -> 11627 (-39.70%)
helped: 1335
HURT: 76
Nops are helped.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22922>
Samuel Pitoiset [Tue, 9 May 2023 09:50:34 +0000 (11:50 +0200)]
radv/ci: stop setting MESA_SPIRV_LOG_LEVEL
Use the default VTN logging level which is warning.
Suggested-by: Emma Anholt <emma@anholt.net>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/6263
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Martin Roukala <martin.roukala@mupuf.org>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22917>
Samuel Pitoiset [Tue, 9 May 2023 09:52:55 +0000 (11:52 +0200)]
spirv: ignore SpvDecorationInvariant warning on struct members
Similar to SpvDecorationRestrict, looks like it's also incorrectly
generated by glslang.
This will allow RADV/CI to leave MESA_SPIRV_LOG_LEVEL as default
(ie. only warnings).
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Martin Roukala <martin.roukala@mupuf.org>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22917>
Simon Ser [Fri, 5 May 2023 15:44:38 +0000 (17:44 +0200)]
radv: advertise LINEAR filter support for multiplanar/subsampled
It seems like radv supports this but doesn't advertise it.
Signed-off-by: Simon Ser <contact@emersion.fr>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22875>
Kurt Kartaltepe [Sun, 7 May 2023 19:55:48 +0000 (12:55 -0700)]
drirc: Set limit_trig_input_range option for Nier games
Resolves ambient occlusion rendering in Replicant
Resolves grass and ocean animations in Automata, and maybe more.
Both of these games have shaders that expect trig values to work across
large ranges with good precision.
Closes #7656
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22894>
Juan A. Suarez Romero [Thu, 27 Apr 2023 12:15:18 +0000 (14:15 +0200)]
v3d: apply proper clamping when setting up RT
Ensure the render target values are in the proper range.
This fixes `spec@!opengl 3.0@render-integer`.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22733>
Juan A. Suarez Romero [Thu, 27 Apr 2023 12:13:14 +0000 (14:13 +0200)]
v3d: upgrade V3D 4.1 to 4.2 version
Some of the new features require at least V3D 4.2. And actually, 4.2 is
the version used by the Raspberry Pi 4 hardware.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22733>
Juan A. Suarez Romero [Thu, 27 Apr 2023 12:11:23 +0000 (14:11 +0200)]
v3d: add per hw-version caller macro
Instead of hardcoding conditionals to know which hardwared-based version
of a function to call, just wrap them in a macro to use
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22733>
Daniel Schürmann [Tue, 25 Apr 2023 17:44:17 +0000 (19:44 +0200)]
radv/rt: store stack_sizes per stage instead of per group
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22503>
Daniel Schürmann [Wed, 26 Apr 2023 10:26:27 +0000 (12:26 +0200)]
radv/rt: use vk_multialloc for radv_ray_tracing_pipeline
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22503>
Daniel Schürmann [Fri, 14 Apr 2023 14:34:27 +0000 (16:34 +0200)]
radv/rt: refactor radv_rt_pipeline_compile()
This patch moves the NIR shader creation into radv_rt_pipeline_compile()
and simplifies radv_rt_pipeline_create().
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22503>
Daniel Schürmann [Fri, 14 Apr 2023 13:50:13 +0000 (15:50 +0200)]
radv/rt: unify radv_rt_pipeline_create() and radv_rt_pipeline_library_create()
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22503>
Daniel Schürmann [Fri, 14 Apr 2023 12:53:02 +0000 (14:53 +0200)]
radv/rt: unify radv_ray_tracing_lib_pipeline and radv_ray_tracing_pipeline
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22503>
Daniel Schürmann [Fri, 14 Apr 2023 12:09:01 +0000 (14:09 +0200)]
radv/rt: change base of radv_ray_tracing_lib_pipeline to radv_compute_pipeline
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22503>
Iván Briano [Tue, 9 May 2023 18:53:37 +0000 (11:53 -0700)]
anv: enable graphics pipeline libraries by default
Since we are disabling mesh, which has issues with gpl, enable gpl by
default now, leaving the renamed environment variable as a way to
disable it for debug purposes.
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Emma Anholt <emma@anholt.net>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22910>
Iván Briano [Mon, 8 May 2023 21:22:15 +0000 (14:22 -0700)]
anv: put EXT_mesh_shader behind an environment variable
We are seeing frequent hangs in other workloads when something using
mesh shaders runs at the same time, so gate the feature behind an
environment variable until we figure out what's going on.
v2: (Sagar)
- Give the mesh enabled variable a more descriptive name
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Emma Anholt <emma@anholt.net>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22910>
Mike Blumenkrantz [Tue, 9 May 2023 14:14:20 +0000 (10:14 -0400)]
zink: also cache swapchain semaphores
a semaphore is a semaphore, as they say
Fixes:
7399b2241f8 ("zink: move semaphore caching to zink_reset_batch_state()")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22935>
Mike Blumenkrantz [Wed, 3 May 2023 17:16:25 +0000 (13:16 -0400)]
zink: block more flushes during unordered blits
Fixes:
89aa3635932 ("zink: block oom flushes during unordered blits")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22931>
Mike Blumenkrantz [Tue, 9 May 2023 23:28:18 +0000 (19:28 -0400)]
zink: adjust bindless texel buffer handle before indexing
buffer handle ids are offset by ZINK_MAX_BINDLESS_HANDLES, but the actual
index is zero-based
Fixes:
99ba529feed ("zink: implement descriptor buffer handling of bindless texture")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22931>
Mike Blumenkrantz [Tue, 9 May 2023 23:17:39 +0000 (19:17 -0400)]
zink: compare desc set to detect bindless vars in separate shaders
the bindless flag here isn't set, so this check did nothing
Fixes:
e3b746e3a31 ("zink: use GPL to handle (simple) separate shader objects")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22931>
Mike Blumenkrantz [Tue, 9 May 2023 22:19:19 +0000 (18:19 -0400)]
zink: bind bindless db set when updating separate shader db sets
this otherwise doesn't bind a bindless set and hangs
Fixes:
e3b746e3a31 ("zink: use GPL to handle (simple) separate shader objects")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22931>
Mike Blumenkrantz [Tue, 9 May 2023 20:32:08 +0000 (16:32 -0400)]
zink: set debug callback on context
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22899>
Mike Blumenkrantz [Tue, 9 May 2023 18:50:36 +0000 (14:50 -0400)]
zink: add perf_debug for "interesting" shader compiles
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22899>
Mike Blumenkrantz [Tue, 9 May 2023 18:45:09 +0000 (14:45 -0400)]
zink: make mesa_logw separate from perf_debug
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22899>
Mike Blumenkrantz [Mon, 8 May 2023 12:54:01 +0000 (08:54 -0400)]
zink: add ZINK_DEBUG=nobgc
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22899>
Mike Blumenkrantz [Fri, 5 May 2023 16:58:03 +0000 (12:58 -0400)]
zink: add ZINK_DEBUG=noopt
it's often useful to disable optimized pipeline compiles for debugging
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22899>
Juan A. Suarez Romero [Tue, 9 May 2023 18:19:16 +0000 (20:19 +0200)]
vc4/ci: disable VC4 jobs
Some test is causing a GPU reset, which blocks merge requests.
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22927>
Jesse Natalie [Tue, 9 May 2023 15:35:08 +0000 (08:35 -0700)]
dzn/ci: Remove 'exclude' for graphicsfuzz cases
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22926>
Jesse Natalie [Tue, 9 May 2023 15:31:56 +0000 (08:31 -0700)]
dzn: Run nir_opt_remove_phis before nir_lower_returns
Otherwise nir_lower_returns can produce invalid NIR by not updating
a phi in a non-trivial if.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22926>
Thong Thai [Mon, 8 May 2023 17:26:10 +0000 (13:26 -0400)]
frontends/va/config: check for QVBR support when creating
Fixes:
30a6363c8f6 ("frontend/va: Support QVBR rate control mode")
Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22905>
Thong Thai [Mon, 8 May 2023 16:20:23 +0000 (12:20 -0400)]
frontends/va/context: check min supported resolution when creating
Fixes:
c987eed9cd7 ("frontends/va: report min width and min height values if available")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8981
Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22905>
Thong Thai [Mon, 8 May 2023 15:43:43 +0000 (11:43 -0400)]
frontends/va/config: add disable packed headers as valid config
Fixes:
306c6e12a59 ("frontends/va: define va av1 encoding caps")
Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22905>
Patrick Lerda [Tue, 25 Apr 2023 14:47:23 +0000 (16:47 +0200)]
radeonsi: set proper drm_amdgpu_cs_chunk_fence alignment
The 'struct drm_amdgpu_cs_chunk_fence' is processed as
'struct drm_amdgpu_cs_chunk_data' which is a union.
This change ensures the proper alignment for this structure
to be processed as 'struct drm_amdgpu_cs_chunk_data'.
The presence of __u64 as one member of
'struct drm_amdgpu_cs_chunk_data' makes the
whole structure expected to be 64-bit aligned.
This is a minor issue detected by the gcc sanitizer (ubsan), for instance at the libdrm library:
../amdgpu/amdgpu_cs.c:937:26: runtime error: member access within misaligned address 0x63100001484c for type 'struct drm_amdgpu_cs_chunk_data', which requires 8 byte alignment
0x63100001484c: note: pointer points here
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
^
Fixes:
ae7e4d7619e0 ("amd: rename ring_type --> amd_ip_type and match the kernel enum values")
Signed-off-by: Patrick Lerda <patrick9876@free.fr>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22920>
José Roberto de Souza [Mon, 17 Apr 2023 15:32:08 +0000 (08:32 -0700)]
iris: Add function to return mmap mode for aux map
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22240>
José Roberto de Souza [Mon, 27 Mar 2023 20:20:45 +0000 (13:20 -0700)]
iris: Add function to return mmap mode for userptr bos
Similar to what was done to alloc buffer but now for userptr bos.
There is no changes in i915 modes but Xe may different values in
future.
While at it, also setting bo->real.heap to IRIS_HEAP_SYSTEM_MEMORY
as it was already implicit set as IRIS_HEAP_SYSTEM_MEMORY is the
value 0 of the enum.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22240>
José Roberto de Souza [Thu, 13 Apr 2023 14:36:53 +0000 (07:36 -0700)]
iris: Add a function to return allocated bo mmap mode
i915 and Xe kmd can have different mmaps modes, so here extracting
the code to handle it to function.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22240>
Matthieu Bouron [Tue, 9 May 2023 10:29:33 +0000 (12:29 +0200)]
lavapipe: honor dst base array layer when resolving color attachments
CC: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22924>
Martin Roukala (né Peres) [Tue, 9 May 2023 12:07:11 +0000 (15:07 +0300)]
zink/ci: document new flakes on RADV
Signed-off-by: Martin Roukala (né Peres) <martin.roukala@mupuf.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22923>
Martin Roukala (né Peres) [Tue, 9 May 2023 11:47:41 +0000 (14:47 +0300)]
zink/ci: document recent fixes on RADV
Signed-off-by: Martin Roukala (né Peres) <martin.roukala@mupuf.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22923>
Samuel Pitoiset [Tue, 2 May 2023 12:46:57 +0000 (14:46 +0200)]
radv: advertise VK_EXT_attachment_feedback_loop_dynamic_state
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22849>
Samuel Pitoiset [Tue, 2 May 2023 13:15:51 +0000 (15:15 +0200)]
radv: implement VK_EXT_attachment_feedback_loop_dynamic_state
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22849>
Mike Blumenkrantz [Wed, 3 May 2023 13:24:26 +0000 (09:24 -0400)]
vulkan/runtime: add VK_DYNAMIC_STATE_ATTACHMENT_FEEDBACK_LOOP_ENABLE_EXT
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22849>
Samuel Pitoiset [Thu, 4 May 2023 12:20:12 +0000 (14:20 +0200)]
vulkan: Update XML and headers to 1.3.250
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/22849>
Mike Blumenkrantz [Mon, 8 May 2023 13:15:08 +0000 (09:15 -0400)]
glsl/lower_samplers_as_deref: apply bindings for unused samplers
if a sampler is never used (no derefs) then its binding will never be
applied here, leaving it with binding=0. this will clobber the real binding=0
sampler in driver backends, leading to errors, so try to iterate using
the same criteria as above and apply bindings in the same way
fixes #8974
cc: mesa-stable
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22902>
Juan A. Suarez Romero [Tue, 9 May 2023 10:51:26 +0000 (12:51 +0200)]
vc4/ci: skip unsupported test versions
Skip all OpenGL[ES] and GLSL tests that are not supported.
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22919>
Samuel Pitoiset [Wed, 3 May 2023 08:05:14 +0000 (10:05 +0200)]
ac/spm: switch to SPM version 2.0
Found this while glancing in PAL.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22817>
Juan A. Suarez Romero [Tue, 9 May 2023 08:17:45 +0000 (10:17 +0200)]
v3d/ci: update neverball-v2 trace reference
Acked-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22915>
Rohan Garg [Fri, 5 May 2023 10:18:59 +0000 (12:18 +0200)]
iris: use the workaround framework for WA
14013111325
Signed-off-by: Rohan Garg <rohan.garg@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22830>
Rohan Garg [Wed, 3 May 2023 14:22:20 +0000 (16:22 +0200)]
hasvk: drop dead code
Signed-off-by: Rohan Garg <rohan.garg@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22830>
Rohan Garg [Wed, 3 May 2023 14:21:04 +0000 (16:21 +0200)]
anv: use the workaround framework for WA
14013111325
Signed-off-by: Rohan Garg <rohan.garg@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22830>
Kenneth Graunke [Thu, 4 May 2023 07:55:42 +0000 (00:55 -0700)]
intel/compiler: Fold constants after distributing source modifiers
This can generate things like fneg! of load_const, which is silly.
Fold those away into an actual constant. Only do so on the scalar
backend because there's a comment above that the vec4 backend doesn't
want any new constants this late, and I'm inclined to believe it.
fossil-db stats show a very minor improvement:
Totals:
Instrs:
203091223 ->
203091099 (-0.00%); split: -0.00%, +0.00%
Cycles:
14410638075 ->
14410577067 (-0.00%); split: -0.00%, +0.00%
Totals from 20 (0.00% of 665070) affected shaders:
Instrs: 27067 -> 26943 (-0.46%); split: -0.47%, +0.01%
Cycles: 2687958 -> 2626950 (-2.27%); split: -2.27%, +0.00%
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22881>
Juston Li [Thu, 27 Apr 2023 21:04:25 +0000 (14:04 -0700)]
venus: enable sparse binding properties
signed-off-by: Juston Li <justonli@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22616>
Juston Li [Thu, 20 Apr 2023 19:48:10 +0000 (12:48 -0700)]
venus: enable sparse binding features
Enable sparse binding now that vkQueueBindSparse works with feedback.
If a device only has queue families with exclusive sparse binding
support then disable sparse binding.
Signed-off-by: Juston Li <justonli@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22616>
Juston Li [Thu, 20 Apr 2023 18:42:35 +0000 (11:42 -0700)]
venus: add back sparse binding support
Add back support for vkQueueBindSparse that works with fence and timeline
semaphore feedback.
For each vkQueueBindSparse batch, if it contains feedback then move the
signal operations to a subsequent vkQueueSubmit with feedback cmds.
This requires queue families that support vkQueueSubmit alongside sparse
binding support so any queue familes that exclusively support sparse
binding will be filtered out.
Signed-off-by: Juston Li <justonli@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22616>
Juston Li [Wed, 19 Apr 2023 19:03:26 +0000 (12:03 -0700)]
venus: add helper function support for VkBindSparseInfo
add getter/setters for VkBindSparseInfo so we can at least share
vn_queue_submission_prepare() to handle external semaphores and
check for fence/semaphore feedback
Signed-off-by: Juston Li <justonli@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22616>
Juston Li [Thu, 20 Apr 2023 21:36:53 +0000 (14:36 -0700)]
venus: filter out queue familes with exclusive sparse binding support
We require the queue to have additional support to be able to send
feedback commands.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22616>
Qiang Yu [Fri, 5 May 2023 03:04:35 +0000 (11:04 +0800)]
ac/nir/cull: fix line position w culling
Fixes:
db0e9d3caba ("ac/nir/ngg: support line culling")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8950
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22867>
Mike Blumenkrantz [Mon, 8 May 2023 19:06:55 +0000 (15:06 -0400)]
zink: fix uncached memory readback
the inner conditional here didn't include uncached readback, meaning
that many (most?) buffers allocated with uncached memory (i.e., BAR) were
being read back directly instead of using staging resources to be faster
at some point this inner conditional should be reevaluated to determine
whether it still does anything, but this is not that time
fixes, among other things, loading in DOOM2016 on some GPUs
Fixes:
52f27cda05b ("zink: allow direct memory mapping for any COHERENT+CACHED buffer")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22907>
Mike Blumenkrantz [Mon, 8 May 2023 23:19:04 +0000 (19:19 -0400)]
zink: block batching of unordered barriers if previous usage was write
in the case where a cmdbuf was submitted with write access and the subsequent
batch promotes an op to unordered, it's important for associated barriers
to happen-before those ops to guarantee synchronization
the fixes tag is wrong on this, but it's all in the same release
Fixes:
bf0af0f8ede ("zink: move all barrier-related functions to c++")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22907>
Mike Blumenkrantz [Mon, 8 May 2023 23:19:04 +0000 (19:19 -0400)]
zink: disable batched unordered barries with ZINK_DEBUG=noreorder
another improvement for debugging
Fixes:
bf0af0f8ede ("zink: move all barrier-related functions to c++")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22907>
Mike Blumenkrantz [Mon, 8 May 2023 21:25:17 +0000 (17:25 -0400)]
zink: flush INDIRECT_BUFFER mem barrier for compute
this is usable in gfx and compute, so don't desync
Fixes:
3674839d110 ("zink: batch mem barrier hooks")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22907>
Mike Blumenkrantz [Mon, 8 May 2023 20:31:58 +0000 (16:31 -0400)]
zink: unbind the ssbo slot being iterated, not the index of the buffer
this otherwise breaks ssbo binding
cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22907>