tu: Rewrite flushing to use barriers

Replace the various ad-hoc flushes that we've inserted, copied from
freedreno, etc. with a unified system that uses the user-supplied
information via vkCmdPipelineBarrier() and subpass dependencies.

There are a few notable differences in behavior:

- We now move setting RB_CCU_CNTL up a little in the gmem case, but
hopefully that won't matter too much. This matches what the Vulkan blob
does.

- We properly implement delayed setting of events, completing our
implementaton of events.

- Finally, of course, we should be a lot less flush-happy. We won't emit
useless CCU/cache flushes with multiple copies, renderpasses, etc. that
don't depend on each other, and also won't flush/invalidate the cache
around renderpasses unless we actually need to.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4964>

tu: Remove useless event_write helpers

tu6_emit_cache_flush() was wrongly named, and with the removal of the
last parameter both are useless.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4964>

tu: Don't actually track seqno's for events

We just dropped the last user which actually cared about the seqno.
This never worked anyway, since the seqno was never reset between
multiple executions of the same command buffer. Turn the part of the
control buffer which used to track the seqno into a dummy dword, and
figure out automatically whether we need to include it. We will
implement seqnos again eventually, with timline semaphores, but that
will likely be totally different.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4964>

tu: Remove useless post-binning flushes

The Vulkan blob doesn't do this, and based on my understanding of how
the blob works this is unnecessary. CACHE_FLUSH is already serialized
against all 3d commands so you don't need to wait for rendering commands
to finish before issuing it, and the subsequent wfi + WAIT_FOR_ME will
cause the CP to wait for the CACHE_FLUSH to finish, so there's also no
need to wait for it to complete. The CACHE_INVALIDATE also seems
unnecessary, and also isn't done by the blob.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4964>

panfrost: Mark PIPE_BUFFER BOs as not renderable

Without this, memory usage explodes by 16x due to height alignment.

Closes: #2715
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4451>

winsys/radeon: do not cast bo->va as void*

Using a util_hash_table_create_ptr_keys to store bo->va address doesn't
work on 32 bits.
This commit makes radeon_drm_winsys::bo_vas a hash_table_u64 instead.

Tested by Miklós Máté.

CC: 20.1 <mesa-stable@lists.freedesktop.org>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3056
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5380>

ci: use separate docker images for baremetal builds

Using arm_test-base as a separate base layer as well for storage &
network bandwidth efficiency.

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/5381>

ci: add arm_test-base docker image

Similar to x86_build-base.

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/5381>

radv/llvm: expose VK_EXT_shader_demote_to_helper_invocation with LLVM 9+

It should already work with the LLVM backend.

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/5361>

glthread: sync in glFlush for multiple contexts

See the code comment.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5382>

gallium/u_vbuf: add a faster path for uploading non-interleaved attribs

+1% higher FPS in torcs.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5304>

gallium/u_vbuf: get rid of some pointer dereferences

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5304>

nir: use bitfield_insert instead of bfi in nir_lower_double_ops

NVIDIA hardware doesn't have an equivilant to bfi, but we do already have
a lowering for bitfield_insert->bfi.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5373>

turnip: fix VFD_CONTROL for binning pass

Fixes some cases with TU_DEBUG=forcebin, specifically the failures in:
dEQP-VK.glsl.*_vertex

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5370>

turnip: use common emit_xs_cntl to fill a6xx_sp_xs_ctrl_reg0

Note this changes the value of SP_GS_CTRL_REG0, by using FOUR_QUADS and
setting MERGEDREGS. ir3 expects MERGEDREGS, and using FOUR_QUADS instead
of TWO_QUADS doesn't seem to hurt.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5370>

turnip: fix HW binning with geometry shader

Fixes failures with TU_DEBUG=forcebin and geometry shaders, for example:
dEQP-VK.binding_model.*geometry*
dEQP-VK.transform_feedback.simple.query*

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5370>

turnip: correctly emit non-binning vs in transform feedback case

The offset given to tu6_emit_shader_object was wrong, binning_vs_offset
should only be used when using the binning pass vs.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5370>

freedreno/a6xx: use nonbinning VS when GS is used

The current "ds = state->bs" seems broken, and the "vs = state->bs" is
unnecessary (already set above). Since it was added as part of a GS-related
patch, I think this is what was intended.

Note: tesselation disables GMEM rendering so we shouldn't have to worry
about hs/ds + binning interaction.

Fixes: 0eebedb6190fdab8956769 ("freedreno/a6xx: Emit program state for GS")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5370>

turnip: clamp sampler minLod/maxLod

Otherwise A6XX_TEX_SAMP_1_{MIN,MAX}_LOD silently overflows.

This fixes these tests:
dEQP-VK.texture.explicit_lod.2d.derivatives.*

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5375>

turnip: update some properties based on blob driver

subTexelPrecisionBits/mipmapPrecisionBits change fixes some failures in:
dEQP-VK.texture.explicit_lod.*

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5375>

turnip: move HLSQ_UPDATE_CNTL write to before xs config writes

This matches the blob and gallium driver more closely, and fixes a
rendering issue observed on a650.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5376>

nir: Fix logic that ends combine barrier sequence

The combination must stop when we see a scoped barrier that have
execution scope, i.e. it has control barrier behavior.  The code was
mistakenly looking at the wrong scope.

Fixes: 345b5847b42 ("nir: Replace the scoped_memory barrier by a scoped_barrier")
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5365>

intel/fs: Add Fall-through comment

Just to clarify the missing break is intentional.

Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5365>

spirv: Memory semantics is optional for OpControlBarrier

Fixes: 3ed2123d77d ("spirv: Use scoped barriers for SpvOpControlBarrier")
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5365>

nir: Fix printing execution scope of a scoped barrier

Fixes: 345b5847b42 ("nir: Replace the scoped_memory barrier by a scoped_barrier")
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5365>

etnaviv: drop translate_blend(..)

PIPE_BLEND_* matches 1:1 the hardware defines.

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/4187>

glsl: inline functions with unsupported return type before converting to nir

glsl_to_nir doesn't expect non-vector/scalar return types in functions.

Fixes: 7e60d5a501f311fa5e7bca5335adc6013dc1aeb9
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3058
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3060
Signed-off-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com>
Tested-by: Witold Baryluk <witold.baryluk@gmail.com>
Reviewed-by: Witold Baryluk <witold.baryluk@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5333>

aco: use v_xor3_b32

fossil-db (Navi):
Totals from 334 (0.26% of 128321) affected shaders:
CodeSize: 3345532 -> 3345484 (-0.00%); split: -0.00%, +0.00%
Instrs: 624662 -> 622778 (-0.30%); split: -0.30%, +0.00%

Mostly affects some parallel-rdp shaders

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5357>

ac/gpu_info, radv: set max_wave64_per_simd to 20 on GFX10

Fixes RADV max_waves reporting for GFX10

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5356>

nir/lower_explicit_io: fix NON_UNIFORM access for UBO loads

Make sure to propagate the NON_UNIFORM access for UBO loads, so
that non-uniform loads are correctly lowered.

Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5311>

nir/spirv/glsl450: increase asin(x) precision

asin(x) is now implemented using a piecewise approximation, which
improves the precision for |x| < 0.5
Previously, we were using a polynomial approximation for both the
asin() and acos() functions. Unfortunately, for asin(), this polynomial
does not have enough precision to satisfy the Vulkan CTS requiremenents,
which define the asin() precision based on the precision of
atan2(x, sqrt(1.0 - x*x)). The piecewise approximation gives the needed
precision in the problematic range.

v2: Skip the piecewise approximation for acos

Closes: #1843
Acked-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3809>

ac/nir: adjust an assertion for D16 on GFX6-GFX7

16-bit types can be used with MUBUF on GFX6-GFX7.

Fixes: c3e0ba52a0a ("ac/nir: support 16-bit data in buffer_load_format opcodes")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5325>

v3d_bufmgr: fix time_t printf

Fixes:

  error: format ‘%ld’ expects argument of type ‘long int’, but argument 3 has type ‘time_t’ {aka ‘long long int’}

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4279>

pan_bo.h: add time.h include for time_t

Fixes:

  ../src/gallium/drivers/panfrost/pan_bo.h:93:9: error: unknown type name ‘time_t’

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4279>

vc4_bufmgr: fix time_t printf

Fixes:

  error: format ‘%ld’ expects argument of type ‘long int’, but argument 3 has type ‘time_t’ {aka ‘long long int’}

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4279>

glsl: fix potential slow compile times for GLSLOptimizeConservatively

See code comment for full description of the change.

Fixes: 0a5018c1a483 ("mesa: add gl_constants::GLSLOptimizeConservatively")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3034
Tested-by: Witold Baryluk <witold.baryluk@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5346>

llvmpipe: do not enable tessellation shader without llvm coroutines support

Tessellation shader in llvmpipe depends on llvm coroutines support. So do not
advertise tessellation shader support in llvmpipe if GALLIVM_HAVE_CORO is FALSE.

This fixes assertion in LLVMTokenTypeInContext() running tessellation shader
tests with llvm version < 6.

Fixes: eb522717 "llvmpipe: add support for tessellation shaders"
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5366>

intel/compiler: fix Android build

Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com>
Fixes: 689acc739899 ("intel/compiler: Extract control barriers from scoped barriers")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3087
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5354>

intel/genxml: Migrate from deprecated xml.etree.ElementTree getchildren.

xml.etree.ElementTree getchildren was deprecated since Python 2.7 and
will be removed in Python 3.9.

Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5348>

android: svga: fix build for GL4.1 support

Fixes the following building errors:

external/mesa/src/gallium/drivers/svga/svga_context.c:184: error: undefined reference to 'svga_init_ts_functions'
external/mesa/src/gallium/drivers/svga/svga_context.c:100: error: undefined reference to 'svga_cleanup_tcs_state'
out/target/product/x86_64/obj_x86/STATIC_LIBRARIES/libmesa_pipe_svga_intermediates/libmesa_pipe_svga.a(svga_state.o):svga_state.c:hw_draw_state_sm5: error: undefined reference to 'svga_hw_tes'
out/target/product/x86_64/obj_x86/STATIC_LIBRARIES/libmesa_pipe_svga_intermediates/libmesa_pipe_svga.a(svga_state.o):svga_state.c:hw_draw_state_sm5: error: undefined reference to 'svga_hw_tcs'

Fixes: ccb4ea5a "svga: Add GL4.1(compatibility profile) support in svga driver"
Signed-off-by: Mauro Rossi <issor.oruam@gmail.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5364>

android: util: fix build for GL4.1 support

Fixes the following building errors:

external/mesa/src/gallium/drivers/svga/svga_state_tgsi_transform.c:154: error: undefined reference to 'tgsi_write_vpos'
external/mesa/src/gallium/drivers/svga/svga_state_tgsi_transform.c:201: error: undefined reference to 'tgsi_remove_dynamic_indexing'

Fixes: 48a7456f ("util: Add util functionality for GL4.1 support")
Signed-off-by: Mauro Rossi <issor.oruam@gmail.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5364>

Switch from cElementTree to ElementTree.

The xml.etree.cElementTree module will be removed in Python 3.9. Since
Python 3.3 the xml.etree.cElementTree module has been deprecated, the
xml.etree.ElementTree module uses a fast implementation whenever
available.

Builds using Python 2.7 can still work but with the slower
implementation.

Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Acked-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5349>

Revert "panfrost: Keep cached BOs mmap'd"

This reverts commit 794c239a990e08b5a42d42607e9c5e5b0921390c.

A kernel bug causes cached BOs to not be unmapped correctly,
triggering "bad page cache" kernel messages and causing short hangs.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5355>

pan/midgard: Use a signed value for checking inline constants

Inline constants are sign extended, so we should use a int16_t instead
of an unsigned type.

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5351>

freedreno/ir3: Handle cases where we decide not to lower UBO 0 loads.

We advertize 4096 vec4s of GL uniform storage, but the HW can only store
512 vec4s in the const buffer.

Closes: #3049
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno/ir3: Drop the max_const on a6xx to 512.

The GLES blob on the p3a limits constlen to 512 between VS and FS across
a6xx gpu ids (615, 630, 640, and 650).  Experimentally, exceeding that
limit in any one stage results in rendering corruption or GPU hangs
(though my most detailed testing had a loop limit in a uniform, so that
may the cause of the hang).  Clamp the limit we use inside of a shader so
we don't exceed it within a stage.

This commit doesn't resovle limiting inter-stage.  Experimentally, I've
found that I can push up to a total of ~768 vec4s between VS and FS on
a630, with or without uniform updates between each draw.  We'll need to do
some shader key-based limiting of constlen at draw time to respect that
limit, but that's left for future work, and this commit is enough for the
google earth case that initiated this work.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno/ir3: Account for driver params in UBO max const upload.

The const state setup needs to be able to push its driver params, so
account for them in the analyze_ubo_ranges.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno/ir3: Stop shifting UBO 1 down to be UBO 0.

It turns out the GL uniforms file is larger than the hardware constant
file, so we need to limit how many UBOs we lower to constbuf loads.  To do
actual UBO loads, we'll need to be able to upload UBO 0's pointer or
descriptor.

No difference on nohw 1 UBO update drawoverhead case (n=35).

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno/ir3: Drop unnecessary alignment of pushed UBO size.

The analysis pass gives us vec4-aligned size, and all of our other
constbuf allocations here are in vec4 units, so we can just divide by 16.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno/ir3: Stop pushing immediates once we've filled the constbuf.

If we filled the constbuf up with UBOs, we may need to avoid generating
more immediate push constants.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno/ir3: Refactor ir3_cp's lower_immed().

There was duplicated handling in the callers that we can just move inside.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno: Upload gallium constbufs as needed when referenced as a UBO.

For now we never ask to set up UBO 0 as a real UBO, so this doesn't
trigger, but it gets us ready for handling the case where UBO 0 is too big
to be push constants in the HW.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5273>

freedreno/a6xx: Add support for ALPHA_TO_ONE.

Fixes piglit ext_framebuffer_multisample-draw-buffers-alpha-to-one

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5343>

turnip: Add support for alphaToOne.

Comparing a blob trace using the feature to one not, the difference was
pretty obvious and in the spot you'd expect compared to alphaToCoverage.
The SP_ reg didn't have a corresponding bit set, though it also has an
alphaToCoverage.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5343>

turnip: Use tu_cs_emit_regs() for BLEND_CONTROL.

Just a cleanup since I was in the area.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5343>

radv: set keep_statistic_info with RADV_DEBUG=shaderstats

Needed for RADV_DEBUG=shaderstats to dump ACO statistics.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5358>

intel: fix gen_sort_tags.py

The script was failing for me (python 3.8), not sure if this is a recent
python version break or not as I don't know how often people have been
running this script:

    Processing ./gen9.xml... Traceback (most recent call last):
      File "./gen_sort_tags.py", line 177, in <module>
        main()
      File "./gen_sort_tags.py", line 170, in main
        genxml[:] = enums + sorted_structs.values() + instructions + registers
    TypeError: can only concatenate list (not "odict_values") to list

Turning the odict into a list fixes it for me, and the resulting xml
file are identical to before :)

Fixes: 903e142f0d35bc550ffd ("genxml: add a sorting script")
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5352>

radv/aco: enable VK_KHR_shader_subgroup_extended_types on GFX6-GFX7

CTS pass on Pitcairn (GFX6). This extension isn't really useful
without 8-bit/16-bit storage though but this is going to be exposed
soon.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5327>

aco: fix nir_intrinsic_quad_* with 8-bit in GFX6-GFX7

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5327>

aco: fix sign-extend 8-bit subgroup operations on GFX6-GFX7

SDWA is GFX8+.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5327>

aco: use v_bfe_u32 for unsigned reductions sign-extension on GFX6-GFX7

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5327>

intel/genxml: drop sort_xml.sh and move the loop directly in gen_sort_tags.py

Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5353>

radv: Use ac_surface to allocate aux surfaces.

For consistency and a bunch of codesharing.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

amd/common: Add total alignment calculation.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Allocate values/predicates at the end of the image.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Disable HTILE in ac_surface.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Disable DCC in ac_surface.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Use offsets in surface struct.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Rely on ac_surface for avoiding cmask for linear images.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Enforce the contiguous memory for DCC layers in ac_surface.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Pass no_metadata_planes info in to ac_surface.

Also do not allocate aux surfaces for multi-plane images. I may
have messed up and used plane 1 offsets for the other planes as well.
I cannot imagine that sharing aux surfaces between the planes will
work well.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

radv: Use ac_surface to determine fmask enable.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5194>

ci: add U-Boot specific fetch strings

U-Boot's fastboot over udp generates the following output:
  Listening for fastboot command on x.y.z.w

Also add a general 'data abort' error string seen with an
too old U-Boot version:
  https://github.com/u-boot/u-boot/commit/95712af

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/5258>

ci: extend expect-output.sh

We need to support different fastboot fetch strings for different
bootloader solutions. Lets extend expect-output.sh to support
multiple fetch strings (-f) and add support for error catch
strings (-e) to stop the CI run early.

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/5258>

freedreno/computerator: fix missing dependency on generated header

Fixes:
```
 ../mesa-freedreno-20.2.0_pre/src/freedreno/computerator/ir3_asm.c:25:10: fatal error: 'ir3/ir3_parser.h' file not found
 #include "ir3/ir3_parser.h"
          ^~~~~~~~~~~~~~~~~~
 1 error generated.
```

Fixes: da467817e3e ("freedreno/ir3: Move ir3 assembler to backend compiler")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5340>

glapi: remove deprecated .getchildren() that has been replace with an iterator

Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3086
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Vinson Lee <vlee@freedesktop.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5342>

radv/aco: enable 64-bit atomic features if RADV is linked with LLVM 8

Just in case someone links RADV with this old LLVM 8 and wants ACO.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5331>

svga: Performance fixes

This is a squash commit of in house performance fixes and misc bug fixes
for GL4.1 support.

Performance fixes:
* started using system memory for constant buffer to gain 3X performance boost with metro redux

Misc bug fixes:
* fixed usage of vertexid in shader
* added empty control point phase in hull shader for zero ouput control point
* misc shader signature fixes
* fixed clip_distance input declaration
* clearing the dirty bit for the surface while using direct map if surface is already flushed
  and there is no pending primitive

This patch also uses SVGA_RETRY macro for commands retries. Part of it is already
used in previous patch.

Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Neha Bhende <bhenden@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5317>

svga: Add GL4.1(compatibility profile) support in svga driver

This patch is a squash commit of a very long in-house patch series.

Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Neha Bhende <bhenden@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5317>

svga/include: Headers for GL4.1 support

This brings in the new types, enums and #defines for GL 4.1
features in the virtual device.

Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Neha Bhende <bhenden@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5317>

winsys/drm: Add GL4.1 support in drm winsys

This is to check whether virtual hardware has SM5 support

Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Neha Bhende <bhenden@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5317>

util: Add util functionality for GL4.1 support

This patch adds the following tgsi utilities

* tgsi_dynamic_indexing: This utility flattens out the dyanamic indexing of constant buffers
* tgsi_vpos: This utility writes zeros to position at index 0 in vertex shader.
  This utility can be used if there is no shader output in vertex shader
* util_make_tess_ctrl_passthrough_shader: This adds passthough tessellation control shader.
  Input of passthrough tess ctrl shader is output of vertex shader
  and output is input of tessellation eval shader.
  If program has tessellation eval shader but no tessellation control shader,
  this utility can be used to create passthrough tessellation control shader.

Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Neha Bhende <bhenden@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5317>

freedreno/a6xx: more early-z

Technically we only have to do late-z in the alpha-test or discard case
if depth-write is enabled.  If depth write is disabled, the depth read /
test / conditional-write interlock that we need to emulate is not a
problem, so we can still use early-z test.

There is a slightly weird case when there is no zsbuf attachment (see
dEQP-GLES31.functional.fbo.no_attachments.*) where the hw wants us to
use LATE_Z.. not entirely sure if this is an interaction with occlusion
query or just a pecularity of how the hw works when there is no depth
buffer.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5336>

ci: bump virglrenderer to latest version

Need this for upcoming GL 4.0 llvmpipe support.

Reviewed-by: Elie Tournier <elie.tournier@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5323>

turnip: Simplify vertex buffer bindings.

We were remapping the bindings so the HW binding points were consecutive,
which there's no need for.  Now that we don't shuffle, we can mostly drop
the dependency on the pipeline for this SDS.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5321>

turnip: Don't bother clamping VB size.

From the VK spec: "All elements of pOffsets must be less than the size of
the corresponding element in pBuffers"

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5321>

turnip: Move vertex buffer bindings to SET_DRAW_STATE.

This means that the HW can skip over the vertex buffer state when it's not
used in a bin.  The blob also has this behavior.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5321>

llvmpipe: move coroutines out of noopt case

the virgl CI code was using the noopt path and crashing with a
wierd can't select llvm.coro.subfn.addr error, turns out we have
to call the cleanup pass no matter what.

This enable a lot more virgl gles31 passes, but we have
to disable tessellation shaders as now they executed, they
crash due to missing OES_gpu_shader5, I should try and reenable
them when llvmpipe is further along

Fixes: d32690b43c91d ("gallivm: add coroutine pass manager support")
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Acked-by: Elie Tournier <elie.tournier@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5320>

pan/mdg: Ensure ld_vary_16 is aligned

Otherwise packing may fail.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Fixes: 5f8dd413bcc ("pan/mdg: Handle 16-bit ld_vary")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5339>

freedreno/a6xx: Fix VFD_CONTROL emit

The FETCH_CNT field isn't actually the FETCH count. We don't have a
lot of data where it's different from DECODE_CNT, so there's not much
to go by. It could be number of VFD_DEST_CNTL or maybe DECODE_CNT for
binning.  For now, setting both to number of DEST_CNTL gets Google
Earth working again.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5324>

radv: Always expose non-visible local memory type on dedicated GPUs

DOOM Eternal expects this type, but RADV doesn't expose it when the VRAM
is entirely host-visible, in my case on Fiji. Matches AMDVLK behavior.

Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/3054
Cc: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5308>

pan/mdg: Legalize inverts with constants

We need to force src_invert to be in the right place even if we flip
when lowering an embedded->inline constant.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Fixes: 449e5ded934 ("pan/mdg: Treat inot as a modifier")
Reported-by: Icecream95 <ixn@keemail.me>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5299>

nir: reuse existing psiz-variable

For shaders where there's already a psiz-variable, we should rather
reuse it than create a second one. This can happen if a shader writes
gl_PointSize, but disables GL_PROGRAM_POINT_SIZE.

Fixes: 878c94288a8 ("nir: add lowering-pass for point-size mov")
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5328>

i965: fix export of GEM handles

We reuse DRM file descriptors internally. Therefore when we export a
GEM handle we must do so in the file descriptor used externally.

v2: Fix dmabuf leak
    Fix GEM handle leaks by tracking exported handles

v3: Check os_same_file_description error (Michel)
    Don't create multiple exports for a given GEM table

v4: Add WARN_ONCE (Ken)

v5: Remove blank line (Ian)
    Remove unused field (Ian)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2882
Fixes: 4094558e8643 ("i965: share buffer managers across screens")
Tested-by: Eric Engestrom <eric@engestrom.ch>
Tested-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4861>

iris: fix export of GEM handles

We reuse DRM file descriptors internally. Therefore when we export a
GEM handle we must do so in the file descriptor used externally.

This change also fixes a file descriptor leak of the FD given at
screen creation.

v2: Don't bother checking fd equals, they're always different
    Fix dmabuf leak
    Fix GEM handle leaks by tracking exported handles

v3: Check os_same_file_description error (Michel)
    Don't create multiple exports for a given GEM table

v4: Add WARN_ONCE (Ken)
    Rename external_fd to winsys_fd

v5: Remove export lock in favor of bufmgr's

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2882
Fixes: 7557f1605968 ("iris: share buffer managers accross screens")
Tested-by: Eric Engestrom <eric@engestrom.ch>
Tested-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4861>

i965: don't forget to set screen on duped image

We'll start using this field more for querying image properties.
Without it we run into a crash.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: <mesa-stable@lists.freedesktop.org>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4861>

iris: fix BO destruction in error path

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: <mesa-stable@lists.freedesktop.org>
Tested-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4861>

mesa: Fix NetBSD compiler macro.

Reported-by: Rafał Mikrut <mikrutrafal54@gmail.com>
Fixes: a63b90712aad ("mesa: also check for __NetBSD__")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3015
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5191>

freedreno/a6xx: also consider alpha-test for ztest-mode

Looks like we don't have CI coverage for this (since deqp==GLES) but
alpha test is conceptually the same as frag shaders with discard, and
should be handled as such.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5298>

freedreno/a6xx: add early-lrz-late-z mode

Now that we are doing a better job of managing LRZ, add support for the
EARLY_LRZ_LATE_Z mode.  Since we properly disable LRZ write in cases
where we don't know a fragment's z value during the binning pass (or
when blend is enabled in a later draw, meaning we will need the earlier
fragment's color), we can enable a mode that keeps the early-lrz test
when the frag shader has kill/discard.  This will only discard geometry
that is definitely not visible.

This is a pretty big win for games/benchmarks that have a lot of frag
shaders with kill/discard.  More than 10% gain for gfxbench trex/mh and
40% gain for mh31.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5298>