radeonsi: improve comments in si_emit_derived_tess_state

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9028>

radeonsi: for tess, determine the minimum num_patches before optimizing tg size

Doing these MINs at the end could have undone optimizations for the LDS
size and threadgroup size, so move the MINs up.

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9028>

ac/surface: use family_id so as not to crash with SI_FORCE_FAMILY in addrlib

We can't invoke gfx6 addrlib (overridden by SI_FORCE_FAMILY) with a gfx9
family ID.

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9028>

radeonsi: fix si_check_render_feedback

si_check_render_feedback only relied on si_images::enabled_mask and
si_samplers::enabled_mask to determine if a texture was being used
both as input and output.

Given that some samplers/images can be considered active (so accounted
for by enabled_mask) but not used by the current shader this could
lead to false-positive.

This commit fixes this by and-ing the above mask with the information
from shader_info for each active shader.

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4227
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8869>

radeonsi: fix read from compute / write from draw sync

A compute dispatch should see the result of a previous draw command.
radeonsi was missing this implicit sync, causing rendering artifacts:
the compute shader was reading from a texture still being written to
by the previous draw.

Framebuffer BOs are marked with RADEON_USAGE_NEEDS_IMPLICIT_SYNC,
so compute jobs will sync.

v2: use RADEON_USAGE_NEEDS_IMPLICIT_SYNC
v3: unconditionally make CB coherent after a flush

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com> (v3)
Reviewed-by: Marek Olšák <marek.olsak@amd.com> (v3)
Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4032
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2878
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/1336
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8869>

radeonsi: store si_context::xxx_shader members in union

This allows to access them individually (sctx->shader.ps) or
using array indexing (sctx->shaders[PIPE_SHADER_FRAGMENT]).

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8869>

radeonsi: fix indentation issue in si_texture.c

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8869>

broadcom/compiler: don't dump shader-db stats for failed shaders

Shaders that fail register allocation were dumped with an instruction
count of 0, so getting them to compile would show up as an instruction
count regression. Also, the LOST/GAINED stats depend on us not dumping
data for failed shaders, which is why we were always seeing 0/0 there.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9077>

broadcom/compiler: use a helper function to decide on TMU spilling

As we add more compiler optimizations that can increase register pressure
we may decide to disallow TMU spilling in more cases so it is probably
better to move this to its own helper function.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9077>

broadcom/compiler: don't emit redundant ldunif

If we emit a new uniform and that uniform has already been emitted
in the same block we can just reuse that.

There is a balancing game here between reducing ldunif instructions
and not increasing register pressure too much though, so we put
a limit to how far back we are willing to look for a previous
definition of the uniform. Based on shader-db results, 20 instructions
produces best results.

total instructions in shared programs: 14928266 -> 14907432 (-0.14%)
instructions in affected programs: 6431841 -> 6411007 (-0.32%)
helped: 15270
HURT: 10772
Instructions are helped.

total uniforms in shared programs: 3944672 -> 3840276 (-2.65%)
uniforms in affected programs: 1827184 -> 1722788 (-5.71%)
helped: 30423
HURT: 845
Uniforms are helped.

total inst-and-stalls in shared programs: 14957813 -> 14936873 (-0.14%)
inst-and-stalls in affected programs: 6475349 -> 6454409 (-0.32%)
helped: 15287
HURT: 10852
Inst-and-stalls are helped.

v2 (Eric):
 - consider ldunifrf too
 - check that no other instruction writes to the register

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9077>

turnip: VK_EXT_memory_budget implementation

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Hyunjun Ko <zzoon@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8524>

turnip: keep track of memory heap usage, size and flags

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Hyunjun Ko <zzoon@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8524>

util: fix parsing of /proc/meminfo MemAvailable value

It was interpreting the value as hexadecimal when it is unsigned.

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Hyunjun Ko <zzoon@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8524>

etnaviv: Fix memory leak in etna_vertex_elements_state_create.

Fix defect reported by Coverity Scan.

Resource leak (RESOURCE_LEAK)
leaked_storage: Variable cs going out of scope leaks the storage it points to.

Fixes: c9e8b49b885 ("etnaviv: gallium driver for Vivante GPUs")
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9034>

intel/fs: Shuffle can't handle source modifiers

On Gen7, we have to split shuffles into two MOVs for 64-bit types so we
can't handle source modifiers.  On Gen12.5, we have to use integer types
all the time so we can't use them there either.  Fixing that will be a
different commit but it interacts with this one.

Fixes: 90c9f29518d "i965/fs: Add support for nir_intrinsic_shuffle"
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9068>

nir/opt_large_constants: Handle generic pointers

We already throw out any variables which may have a complex use so we
just need to make sure that our mode checks don't assert if we have a
deref which may_be but not must_be nir_var_function_temp.

Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9068>

nir: Fix parameter order in the bcsel-of-shuffle optimization

Fixes: 4ff4d4e56966a40 "nir/opt_intrinsic: Optimize bcsel(b, shuffle..."
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9068>

nir: Don't optimize bcsel-of-shuffle across blocks

We can't move the shuffle to a new block so this only works if the
shuffle and the bcsel are in the same block.  Fortunately, in the
motivating case, this is true.

Also, we have to be careful around discard.  We could try really hard to
just avoid moving them past discard but we choose to simply bail if we
see a discard instead.

Fixes: 4ff4d4e56966a40 "nir/opt_intrinsic: Optimize bcsel(b, shuffle..."
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9068>

nouveau: Use format modifiers in buffer allocation

The nvc0 nouveau backend already claimed to support format modifiers, but
in practice it ignored them when allocating buffers outside of a
perfunctory check for the linear modifier in the first element of the
format modifier list.

This change deduces the supported modifiers, if any, for a given miptree
creation request, prioritizes them based on performance and memory waste
properties, compares the requested modifiers against the prioritized list
of supported modifiers, and overrides the internal layout calculations
based on the layout defined by the resulting modifier.

Additionally, if modifiers are provided and none are compatible with the
miptree creation request, the function now fails.  This brings the nouveau
behavior in line with other drivers such as i965 and etnaviv.

Signed-off-by: James Jones <jajones@nvidia.com>
Tested-by: Karol Herbst <kherbst@redhat.com>
Tested-by: Simon Ser <contact@emersion.fr>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3724>

nouveau: no modifier != the invalid modifier

Other drivers fail resource allocation when a list of modifiers for the
resource is provided but none are supported. This includes cases when the
never-supported DRM_FORMAT_MOD_INVALID modifier is explicitly passed.  To
enable matching that functionality in nouveau, use an empty modifier list
rather than creating a one-entry list containing only
DRM_FORMAT_MOD_INVALID when the non-modifier resource creation function is
used.

This change stops short of failing allocations when no modifier is
specified, because the current code ignores all modifiers except the linear
modifier when creating resources, so there is not yet a framework in place
to determine which modifiers are valid for a given resource creation
request, and hence no way to reject only those which are invalid.

Signed-off-by: James Jones <jajones@nvidia.com>
Tested-by: Karol Herbst <kherbst@redhat.com>
Tested-by: Simon Ser <contact@emersion.fr>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3724>

nouveau: Use DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D

Replace existing usage of the NVIDIA_16BX2_BLOCK format modifiers with
parameterized use of the more general macro.  Nouveau will now report
support for slightly different modifiers depending on whether the
underlying chip is a tegra GPU or not, and will potentially report valid
format modifiers for more resource types, but overall this should be a
functional no-op for existing applications.

Signed-off-by: James Jones <jajones@nvidia.com>
Tested-by: Karol Herbst <kherbst@redhat.com>
Tested-by: Simon Ser <contact@emersion.fr>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3724>

nouveau: Stash supported sector layout in screen

Older Tegra GPUs use a different sector bit swizzling layout than desktop
and Xavier GPUs. Hence their format modifiers must be differentiated from
those of other GPUs.  As a precursor to supporting more expressive block
linear format modifiers, deduce the sector layout used for a given GPU from
its chipset and stash the layout in the nouveau screen structure.

Signed-off-by: James Jones <jajones@nvidia.com>
Tested-by: Karol Herbst <kherbst@redhat.com>
Tested-by: Simon Ser <contact@emersion.fr>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3724>

zink: add a disk cache for pipeline objects

this writes the pipeline cache to disk on shutdown

ideally we'd rather write this incrementally any time we make a new pipeline,
but that ends up breaking the disk cache infrastructure since we're always writing
to the same file, so this is the best we can do for now

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9094>

zink: create a VkPipelineCache object on the screen and use it

this enables reuse of shaders across pipelines

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9094>

zink: hook up valid_buffer_range for buffer resources using util_range

this lets us avoid stalling during transfer map in some cases

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9062>

zink: add flag for no-oping fence finish

if a fence hasn't been activated then we don't need to wait on it

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9067>

freedreno/ir3: Add missing shader prog cache invalidation

I'm not aware of actually hitting this case, but we need to consider
more than just vs/fs when shader state is deleted.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/ir3: Async shader compile

Draw-time variants are still synchronous, but I'm not sure there is much
(easy) benefit from generating them asynchronously.  Without patching
the cmdstream later before batch submit, we'd end up waiting for them
immediately.  But we should mostly only hit draw-time variants for
desktop GL (and mostly legacy features).

Note: new xfb xfail on a5xx, but most of the xfb tests are already xfail
so I think we just managed to change the timing a bit, rather than this
being related to async compile.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3857
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/ir3: Reshuffle compute state creation

There was just a single remaining caller of ir3_shader_create_compute(),
so fold that into ir3_shader_compute_state_create().

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/ir3: Reshuffle ir3_shader_create()

This had only a single caller, so no need to be exported.  With
that done, fold the ir3_shader creation (ie. the cheap part) into
ir3_shader_state_create(), and rename what is left.

This is prep to moving initial variant creation to a work queue.

It does slightly change the error handling, in that we don't
cleanup the shader hwcso.  We wouldn't be able to do this anyways
with async compile.  But it ends up using the same error handling
paths that we'd hit if we got a compile failure for a draw-time
variant.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/ir3: Add ir3_screen_fini()

Move ir3_compiler_destroy() into ir3_screen_fini().  This gives us a
good place to cleanup an sync compile queue.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/ir3: Move ir3_compiler_create()

All the ir3 using backends already call ir3_screen_init(), so lets just
move compiler creation there.

In a subsequent patch, we'll add initialization of the queue for async
compile.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/ir3: Add ir3_shader_state

Initially just a wrapper for ir3_shader, but this is where we'll hook in
the bookkeeping for async compile.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/ir3+a5xx+a6xx: De-duplicate create_compute_state()

These were identical between a5xx and a6xx, so move into shared helper
that can be directly plugged into pctx, similar to the various 3d shader
state creation.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/a6xx: Drop fd6_compute_stateobj

It wasn't really doing anything useful.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno/a5xx: Drop fd5_compute_stateobj

It wasn't really doing anything useful.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

freedreno: Misc cleanup

Some whitespace cleanup + comment addition.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8795>

zink: use nir_shader_instructions_pass for draw params pass

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9090>

clover: Add -fgnu89-inline to Clang command line

Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9085>

microsoft/clc: Add test with inline function

Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9085>

microsoft/clc: Add -fgnu89-inline to clang args

Without this, inline functions don't have their body emitted in the
resulting LLVM IR, meaning the kernel will fail to link.

Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9085>

spirv: Delete the impl for prototype-only functions

Previously, when we had a prototype-only function in SPIR-V, we would
compile it just fine and the function would have an impl that did
nothing.  This commit changes that so that the nir_function::impl is
NULL to indicate a prototype-only function.

Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9069>

spirv: Store the nir_function in vtn_function

This is a better mapping as not all nir_functions have impls.

Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9069>

zink: add nir_intrinsic_memory_barrier_image handling

this is the last one

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9087>

frontends/va : Fix memory leaks incase of error returns

Incase of error returns missed the free calls for config and context.
This patch handling in freeing them

Signed-off-by: SureshGuttula <sguttula@amd.com>
Reviewed-by: Vinson Lee <vlee@freedesktop.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8993>

CI: Use a sha for the Windows SPIRV-LLVM-Translator dependency

Acked-by: Daniel Stone (daniels@collabora.com)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9018>

zink: fix device codegen extension detection

the logic for this was broken and failed to detect any extensions other
than the first one listed. instead, we must follow this logic chain:
1. check the extension name
  2a. if this is an extension that got promoted to core, check the @since version
    3a. if current version >= @since version
      4a. if the extension has required features/properties, check those
      4b. else set supported
    3b. else
      4a. if the extension has required features/properties, check those
      4b. else set supported
  2b. else
    4a. if the extension has required features/properties, check those
    4b. else set supported

Fixes: efe6f00e345 ("zink/codegen: do not enable extensions that are now core")
Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9081>

nir/algebraic: Covert up-cast of down-cast to extract on Intel

This starts generating extract for bit sizes other than 32 but our
back-end handles that just fine.

Reviewed-by: Ian Romanick <ian.d.romanick@.intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8872>

nir/algebraic: Clean up up-cast of down-cast when we can

There are a bunch of cases where we can pretty quickly determine that
the high bits don't matter.  In these cases, delete the casts.

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8872>

nir: Add some range analysis for used bits

This isn't 100% accurate, of course, but it should be good enough for
what we're about to do with it.

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8872>

intel/nir: Lower 8-bit phis on Gen11+

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8872>

nir/lower_bit_size: Support phi instructions

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8872>

nir: Add a couple helpers for phis and cursors

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8872>

virgl: Return total video memory if available

Signed-off-by: Rohan Garg <rohan.garg@collabora.com>
Reviewed-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9009>

virgl: update headers

Signed-off-by: Rohan Garg <rohan.garg@collabora.com>
Reviewed-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9009>

frontends/va/config: Fix check for packed header config

Fixes: b4651890be4 ("frontends/va: Update conditional checks for code stability.")
Signed-off-by: Thong Thai <thong.thai@amd.com>
Tested-by: James Zhu <James.Zhu@amd.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4285
Reviewed-by: Leo Liu <leo.liu@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9020>

gitlab-ci: add intel APL and GLK devices with manual triggers

This add support for the Intel Apollo Lake and Gemini Lake families,
however the job will be disabled by default unless the developer
manually hit play for the iris-apl-traces and iris-glk-traces jobs in
GitLab CI.

These devices are still under experimental level support in
the Lava lab and are not guaranteed to work reliably yet. Once they
become reliable and more resilient we will enable them by default in
MesaCI.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8162>

gitlab-ci: build the iris gallium driver as well

For now we will start with iris. Our main focus is to enable the devices
to be used in MesaCI.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8162>

gitlab-ci: extend x86_64 kernel config to suport Intel devices

There are extra kernel config options we need to enable for Intel.

Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8162>

intel/compiler: Free resources on test teardown

Ensure that all resources are properly released by
properly parenting them to a memory context and releasing
the context during test teardown.

Signed-off-by: Rohan Garg <rohan.garg@collabora.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8162>

intel/genxml: Free resource before exiting

Signed-off-by: Rohan Garg <rohan.garg@collabora.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8162>

pan/bi: Use the correct size for UBO loads

Multiply by the destination bit size to get the number of bits to
load instead of assuming 32 bits.

Fixes: 2e57684d2d3 ("pan/bi: Implement load_ubo with the builder")
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9071>

radv: Do pipe misalignment check per plane.

Fixes: 4c99d6ff54b ("radv: flush L2 for images affected by the pipe misaligned issue on GFX10+")
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9078>

broadcom/compiler: Merge instructions more efficiently

Instructions are allowed to access up to two rf registers, or one rf
register and a small immediate. This change allows qpu_merge_inst to
take full advantage of this by allowint the merging of two instructions
if they have no more than two different rf registers between them,
or one rf register and one small immediate. qpu_merge_inst rewrites
the instructions as needed to pack everything into raddr_a and raddr_b
in the merged instruction.

shader-db stats:
total instructions in shared programs: 19938769 -> 18929664 (-5.06%)
instructions in affected programs: 17929438 -> 16920333 (-5.63%)
helped: 95008
HURT: 242
helped stats (abs) min: 1 max: 785 x̄: 10.62 x̃: 7
helped stats (rel) min: 0.30% max: 21.25% x̄: 5.37% x̃: 4.98%
HURT stats (abs)   min: 1 max: 2 x̄: 1.10 x̃: 1
HURT stats (rel)   min: 0.30% max: 3.12% x̄: 1.62% x̃: 1.54%
95% mean confidence interval for instructions value: -10.67 -10.52
95% mean confidence interval for instructions %-change: -5.37% -5.33%
Instructions are helped.

total max-temps in shared programs: 3122664 -> 3112446 (-0.33%)
max-temps in affected programs: 124881 -> 114663 (-8.18%)
helped: 5445
HURT: 0
helped stats (abs) min: 1 max: 15 x̄: 1.88 x̃: 1
helped stats (rel) min: 1.49% max: 40.54% x̄: 8.97% x̃: 6.67%
95% mean confidence interval for max-temps value: -1.91 -1.84
95% mean confidence interval for max-temps %-change: -9.12% -8.81%
Max-temps are helped.

total sfu-stalls in shared programs: 38028 -> 41231 (8.42%)
sfu-stalls in affected programs: 6053 -> 9256 (52.92%)
helped: 664
HURT: 3380
helped stats (abs) min: 1 max: 2 x̄: 1.04 x̃: 1
helped stats (rel) min: 9.09% max: 100.00% x̄: 70.81% x̃: 100.00%
HURT stats (abs)   min: 1 max: 4 x̄: 1.15 x̃: 1
HURT stats (rel)   min: 0.00% max: 300.00% x̄: 46.39% x̃: 25.00%
95% mean confidence interval for sfu-stalls value: 0.76 0.82
95% mean confidence interval for sfu-stalls %-change: 25.03% 29.26%
Sfu-stalls are HURT.

total inst-and-stalls in shared programs: 19976797 -> 18970895 (-5.04%)
inst-and-stalls in affected programs: 17963129 -> 16957227 (-5.60%)
helped: 95017
HURT: 245
helped stats (abs) min: 1 max: 785 x̄: 10.59 x̃: 7
helped stats (rel) min: 0.30% max: 21.25% x̄: 5.35% x̃: 4.95%
HURT stats (abs)   min: 1 max: 2 x̄: 1.09 x̃: 1
HURT stats (rel)   min: 0.30% max: 3.12% x̄: 1.61% x̃: 1.54%
95% mean confidence interval for inst-and-stalls value: -10.64 -10.48
95% mean confidence interval for inst-and-stalls %-change: -5.35% -5.31%
Inst-and-stalls are helped.

v2 (Iago):
 - moved early return for naddrs > 2 even earlier.
 - only update {add,mul}.b mux if instruction has more than one operand.
 - don't OR b->raddr_{a,b} if we are not merging add/mul instructions.
 - don't initialize packed to 0.
 - minor style fixes.

Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9026>

meson: invalid keyword argument dependencies

Fixes: e4cc52c0 (vulkan: Add common extension tables)
Reviewed-by: Dylan Baker <dylan.c.baker@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8821>

radv: only apply the MRT output NaN fixup to non-meta shaders

We only want this workaround to be applied for game shaders.

Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4163
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/9048>

ci: Update baremetal kernel to 5.11 plus patches

For imx6 we need the following fec ethernet fix:
 c730ab423bfa ("net: fec: Fix temporary RMII clock reset on link up")

Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9046>

lavapipe: add support for missing 10/10/10/2 formats.

The snorm formats don't work for blitting, so don't expose
them for that.

This passes all CTS tests that it enables.

Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8907>

lavapipe: add support for 2/10/10/10 scaled formats.

These will be used for zink CI testing.

Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8907>

llvmpipe: don't support scaled formats outside vertex buffers

Scaled formats are usually only needed as vertex buffer formats,
don't expose them as supported for other things.

Lavapipe will use this to export the correct formats support.

Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8907>

util/format: add helper to check if a format is scaled.

lavapipe/llvmpipe need this to rule out scaled formats for non-vertex
format usage. Note NONE is defined as scaled in u_format, but for
the purposes of this helper I don't want it to be considered scaled.

Reviewed-by: Adam Jackson <ajax@redhat.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8907>

zink: support nir_intrinsic_group_memory_barrier

needed for cts

Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9073>

features: mark off GL 4.6 and ES 3.1 for zink

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: GLSL 460

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: PIPE_CAP_GL_SPIRV

still needs a bunch of fixing, but 75% of tests pass

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: enable pipeline statistics cap

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: enable PIPE_CAP_QUERY_SO_OVERFLOW

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: enable PIPE_CAP_POLYGON_OFFSET_CLAMP

this is already handled

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: enable PIPE_CAP_DRAW_PARAMETERS

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: enable PIPE_CAP_TGSI_VOTE

ARB_shader_group_vote

Acked-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9072>

zink: add util function for submitting the compute batch

sometimes we just want to submit this and not wait on it

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9063>

zink: rewrite drawid based on shader key value

same as basevertex

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: break out push constant creation in compiler and add drawid value

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: add a vs shader key for rewriting gl_DrawID

if we get a direct draw, we have to rewrite the drawid for it to work as expected

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: add a draw_id param to vs push constants

gallium always gives us multidraws as individual draws, so we need to feed
this through to the shader

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: wrap shader gl_BaseVertex access with a bcsel based on push constant state

vulkan has different mechanics than gl for this variable based on whether the
current draw is indexed, so we need to rewrite the access here for that case

this also requires that we add some padding to the tcs shader injection to
account for new members being added to the push constant

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: add push constant value to indicate whether the current draw is indexed

due to semantic differences between gl and vk variables, this is going to be
necessary for gl_BaseVertex

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: rework tcs injection to be more compatible with new push const struct

we can simplify the push constant loader to directly take the struct member
index here and then pass that directly to simplify things for future use

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: create a struct for tracking push constant layout

it'll be helpful to update this as we add more values here so we can
avoid having to update all the users

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: add handling for ARB_shader_draw_parameters variables in ntv

* gl_DrawID
* gl_BaseVertex
* gl_BaseInstance (was already semi-handled)

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8971>

zink: handle 1bit undef values in ntv

spirv requires that 1bit values be bool types, not uints

Fixes: 93af00502eb ("zink: use uvec for undefs")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9059>

zink: fix slot mapping for legacy gl io with tess stages

e.g., gl_BackColor is a thing

Fixes: aec03553e1b ("zink: fix tess shader i/o variables")
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9019>

zink: add support for pipeline statistics queries

so easy!

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9010>

zink: hook up cs invocation queries to the compute batch

compute batches are separate, so we have to run these queries on the
appropriate batch to see the expected results

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9010>

zink: unset generated TCS if its parent TESS is unset

ensure this doesn't get pulled in during the next program update

Fixes: 334759d8509 ("zink: implement passthrough tcs shader injection")
Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9057>

aco: fix assertion in insert_exec_mask pass

Fixes: a56ddca4e80a6ef7bb0c44edb4e5b6169510aaca ('aco: make all exec accesses non-temporaries ')
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9047>

aco: fix transition_to_{WQM,Exact} if exec.back() is not in exec

This can happen at merge blocks.

fossil-db (GFX10.3):
Totals from 25229 (17.25% of 146267) affected shaders:
CodeSize: 58575920 -> 58571376 (-0.01%); split: -0.01%, +0.00%
Instrs: 10979245 -> 10978109 (-0.01%); split: -0.01%, +0.00%
SClause: 591817 -> 591816 (-0.00%)
Copies: 604987 -> 603851 (-0.19%); split: -0.19%, +0.00%
Cycles: 96088796 -> 96084252 (-0.00%); split: -0.00%, +0.00%
VMEM: 10470372 -> 10470368 (-0.00%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: a56ddca4e80 ("aco: make all exec accesses non-temporaries")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4299
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9047>

mesa: add debug code to catch missing _mesa_update_valid_to_render_state calls

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8798>

mesa: inline draw validate functions

This just moves the functions to draw.c.

Our CPU overhead is so low now that this increases performance by a few %.

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8798>

mesa: inline _mesa_set_draw_vao and set_varying_vp_inputs for draw calls

This just moves the functions to draw.c. It's inlined because the function
name disappears in the profiler. It improves performance.

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8798>