radeonsi: bind shader images after DCC is disabled for image stores

This prevents an infinite recursion with a compute-based DCC decompression
when it restores shader images.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4761>

radeonsi: clean up and deduplicate code around internal compute dispatches

In addition to the cleanup, there are these changes in behavior:
- clear_render_target waits for idle after the dispatch and then flushes
  L0-L1 caches (this was missing)
- sL0 is no longer invalidated before the dispatch, because src resources
  don't use it
- sL0 is no longer invalidated after the dispatch if dst is an image

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4761>

radeonsi: unify and align down the max SSBO/TBO/UBO buffer binding size

Rounding down the size fixes:
    KHR-GL45.enhanced_layouts.ssb_member_invalid_offset_alignment

Fixes: 03e2adc990d239119619f22599204c1b37b83134
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4761>

tgsi_to_nir: handle TGSI_OPCODE_BARRIER

Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4761>

tgsi_to_nir: handle TGSI_SEMANTIC_BLOCK_SIZE

Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4761>

glthread: upload non-VBO vertices and indices for non-Indirect non-IBM draws

This is basically the same thing u_vbuf does.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: handle gl{Push,Pop}ClientAttrib{DefaultEXT} for glthread states

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: handle POS vs GENERIC0 aliasing

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: initialize VAOs properly

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: track primitive restart state

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: track instance divisor changes

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: track pointers and strides for Pointer & EXT_dsa attrib functions

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: don't use atomics for refcounting to decrease overhead on AMD Zen

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

glthread: do glBufferSubData as unsynchronized upload + GPU copy

1. glthread has a private upload buffer (as struct gl_buffer_object *)
2. the new function glInternalBufferSubDataCopyMESA is used to execute the copy
   (the source buffer parameter type is struct gl_buffer_object * as GLintptr)

Now glthread can handle arbitrary glBufferSubData sizes without syncing.

This is a good exercise for uploading data outside of the driver thread.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: add _mesa_InternalBind{ElementBuffer,VertexBuffers} for glthread

Uploaded non-VBO user data will be set via these functions.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: add glInternalBufferSubDataCopyMESA for glthread

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: inline vbo_context inside gl_context to remove vbo_context dereferences

The number of lines in the disassembly of vbo_exec_api.c.o decreased
by 4.5%, which roughly corresponds to a decrease in instructions
for immediate mode thanks to the removal of ctx->vbo_context dereferences.

It increases performance in one Viewperf11 subtest by 2.8%.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa,st/mesa: add a fast path for non-static VAOs

Skip most of _mesa_update_vao_derived_arrays if the VAO is not static.
Drivers need a separate codepath for this.

This increases performance by 7% with glthread and the game "torcs".

The reason is that glthread uploads vertices and sets vertex buffers
every draw call, so the overhead is very noticable. glthread doesn't
hide the overhead, because the driver thread is the busiest thread.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: don't update shaders on fixed-func state changes if user shaders are bound

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: don't set unnecessary program flags in _mesa_update_state

_NEW_PROGRAM is already set.
_NEW_FRAG_CLAMP is not used by the fixed-func fragment shader.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: set _NEW_FRAG_CLAMP only when needed

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: don't call _mesa_update_state for _mesa_get_clamp_fragment_color

It's not needed.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

st/mesa: Move _NEW_FRAG_CLAMP to NewFragClamp driver flag.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

mesa: optimize glPush/PopClientAttrib by removing malloc overhead

just declare all structures needed by the stack in gl_context.

This improves performance by 5.6% in the game "torcs". FPS: 101.01 -> 106.73

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>

freedreno/a6xx: don't set SP_FS_CTRL_REG0.VARYING for fragcoord

Similar change to 5785bcc8a0ff9c5072c647337bf73f696c63cbe6.  It appears
on a6xx and in fact this could cause varying corruption before the FS
had a chance to consume the varyings from varying storage.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2838
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4838>

iris: don't assert on unfinished aux import in copy paths

After a resource is created the first command using it could be a copy
command.

In iris_state we finish the import on surface/view creation but we
don't do that for copies.

v2: Move finish call to gallium entrypoints (Ken)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: <mesa-stable@lists.freedesktop.org>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2725
Reviewed-by: Tapani Pälli <tapani.palli@intel.com> (v1)
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4657>

freedreno: sync registers with envytools

Pull in the `SP_xS_BRANCH_COND` regs to keep the mesa and envytools
copies from getting out of sync.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: more OUT_REG()

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno: scissor vs disabled scissor micro-opt

We don't need to deref and check rast state every time scissor changes,
only when rast state changes.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: convert const emit to OUT_PKT()

This is another hot packet.  This splits out each of the four cases
(geom vs frag, and indirect vs inline) intentionally, to avoid some
parity bit calc.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/ir3: inline const emit

Drop vfunc callbacks for per-gen packet emit, and instead have a header
that is #include'd once per gen.

We'll end up with multiple copies of some of this, but since we never
have multiple gen's of adreno on a single device, only one copy will be
paged in (and hopefully in the I-cache for hot-paths)

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: split out const emit

In order to inline the const emit and drop the per-gen vfuncs to emit
the correct sort of packet, we should consolidate all of the entry-
points to const emit in one object file, otherwise we'll end up with
multiple copies per gen.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: convert draw packet to OUT_PKT()

This is one of the hotter pkt7 packets, since it is guaranteed to happen
on every draw.  Switch to OUT_PKT() for less driver overhead in the draw
path.

Slight bit of cheating for using CP_DRAW_INDX_OFFSET_0 for the first
dword in all cases.  Possibly *gen_header.py* could be more clever
and use typedef's in the cases of bitsets like vgt_draw_initiator.
But this works out because it is always the first dword.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: add OUT_PKT()

Similar to OUT_REG(), this has the benefits of:

1. No more messing up pkt size
2. Detects errors of mixing up the order of dwords in the packet
3. Optimizes to more efficient code

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: skip unnecessary MRT blend state

To lower CP overhead.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: combine sample mask into blend state

This gets rid of one lone register we used to emit directly in IB2
whenever blend state changes, at the expense of needing blend state
variants when sample-mask changes.  I think typically sample-mask
should not change frequently, so this seems like a fair trade-off.

To further limit the # of variants, we ignore sample-mask bits that
are not relavant for the current # of samples.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: move blend-color to stateobj

To reduce CP overhead for draws skipped in a bin.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: limit LRZ state emit

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: limit PROG_FB_RAST state emit

The dependency on RASTERIZER state is only when rasterizer_discard
changes.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: move scissor state to stateobj

To reduce CP overhead for draws skipped in a given tile.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: move const state to single stateobj

In practice, we end up updating all the shader stages at the same time.
So collapse this into a single group.

Reduces CP overhead.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: avoid unnecessary clearing VS DP state

If there is no (potentially unflushed) VS driver-param state, we don't
need to emit a DISABLE on each frame.  So avoid that to reduce CP
overhead.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/a6xx: small query cleanup

Don't open-code `fd6_event_write()`

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/drm: inline the things

The existing structure dates back to when this code was part of libdrm,
and we wanted some of this not to be exposed as ABI between libdrm and
mesa.  Now that this is no longer a constraint, inline things.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/drm: drop atomic refcnts

Since we dropped the async flush_queue, we no longer need the refcnts to
be atomic.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4813>

freedreno/ir3: Initialize the unused dwords of the immediates consts.

Avoids having spurious differences (and weird values to look at!) in
traces from uninitialized memory.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4824>

Revert "anv/gen12: Temporarily disable VK_KHR_buffer_device_address (and EXT)"

This reverts commit c61ad77cd260ce7666b257ce411e512e0ca12ec8.  We now no
longer have a problem with these.

Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4819>

intel/eu: Use non-coherent mode (BTI=253) for stateless A64 messages

We don't care about full IA coherency since we always have the
opportunity in GL or Vulkan to flush the data cache.  Using IA-coherent
mode is likely just making A64 access slower than it needs to be.

Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4819>

pan/decode: Use correct printf modifier for long int

As reported by Coverity:
>>>     CID 1462605:  API usage errors  (PRINTF_ARGS)
>>>     Argument "p->zero5" to format specifier "%x" was expected to have type "unsigned int" but has type "unsigned long".

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4724>

pan/decode: Check for correct unknown field

As reported by Coverity:

>>>     CID 1462606:  Incorrect expression  (COPY_PASTE_ERROR)
>>>     "unk1" in "s->unk1" looks like a copy-paste error.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4724>

panfrost: Don't leak temporary descriptors array

As found by Coverity:

>>>     CID 1462596:  Resource leaks  (RESOURCE_LEAK)
>>>     Variable "descriptors" going out of scope leaks the storage it points to.

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4724>

panfrost: Emit blend descriptors on Bifrost

Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4724>

panfrost: Enumify bifrost blend types

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4724>

gitlab-ci: update tracie README after changes in main script

v2:
  - Update the default location for the traces when there is no
    traces-db entry in the traces definition file (Alexandros).

Fixes: 90a39af5f65 "(ci: Drop the git dependency in tracie)"
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Alexandros Frantzis <alexandros.frantzis@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4640>

.mailmap: add an alias for Andres Gomez

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4739>

.mailmap: add an alias for Iago Toral Quiroga

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4739>

ci: Add intel to shaderdb runs

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Acked-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4594>

intel: add stub_gpu tool

Run shaderdb like this :

   intel_stub_gpu -p bxt ./run ./shaders/*

List of platform names is available from
gen_device_name_to_pci_device_id() (src/intel/dev/gen_device_info.c).

v2: Add missing getparam support
    Raise max soft limit of file descriptors

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Acked-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4594>

intel/dev: print out error when platform is not found by name

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Acked-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4594>

drm-shim: silence warnings

Matt is seeing a bunch of warnings :

   drm_shim.c:312:4: warning: ignoring return value of ‘asprintf’, declared with attribute warn_unused_result [-Wunused-result]

v2: Add nofail variants of *asprintf (Eric)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4594>

drm-shim: don't create a memfd per BO

Running shader-db on big servers with many cores, we're running out of
file descriptors.

Use a single 4Gb memfd instead and allocate from it using a VMA.

v2: Align VMA allocation to 4096 (Eric)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4594>

drm-shim: move handle lock to shim_fd

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4594>

gallium: extract out logicop helper

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4826>

gallivm: fix half to float conversions with llvm 11

LLVM 11 removes the intrinsic for half to float conversion, so use the fpext
function instead. This function actually works now with half to float, albeit
a quick experiment showed at least the x86 backend cannot lower it itself if
the cpu doesn't support it natively and tries to call external library, which
crashes (and would be very slow anyway as it would be lowered to scalar code),
so for now only use it where we previously used the f16c intrinsic.

Closes: https://gitlab.freedesktop.org/mesa/mesa/issues/2603
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4800>

cut 20.1 branch

Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4823>

intel/ir: Update performance analysis parameters for memory fence codegen changes.

The SFID field of the SHADER_OPCODE_MEMORY_FENCE and
SHADER_OPCODE_INTERLOCK instructions now indicates the target function
of the memory fence.  Account the cycle-count cost to the right shared
unit.

Fixes: f858fa26b4cca8834c8687f01d2ba431fcc8e006 ("intel/fs,vec4: Pull stall logic for memory fences up into the IR")
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4817>

docs: update calendar, add news item, and link releases notes for 20.0.6

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4822>

docs: Add SHA256 sums for 20.0.6

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4822>

docs: Add release notes for 20.0.6

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4822>

pan/mdg: Be a bit more pedantic in invert passes

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4820>

pan/mdg: Track more types

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4820>

freedreno: fix buffer import

`rsc->layout.cpp` is zero until we `fd_resource_layout_init()`

Fixes: 5a8718f01b3 ("freedreno: Make the slice pitch be bytes, not pixels.")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4818>

i965: remove unused variable

Last use was removed in 54525808aa58.

Signed-off-by: Marcin Ślusarz <marcin.slusarz@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4809>

radv: Fix implicit sync with recent allocation changes.

the implicit sync flag gets set at the beginning at the function,
but I used = instead of |= later.

Fixes: bec92850270 "radv: Stop using memory type indices."
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4814>

freedreno: switch to simple_mtx

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4810>

freedreno: add screen lock wrappers

This will make it easier to swap out to simple_mtx_t

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4810>

util/simple_mtx: add assert_locked()

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4810>

turnip: fix wrong substream size in parse_multisample_and_color_blend

Missed updating this when adding tu6_emit_sample_locations

Fixes: a92d2e11095 ("turnip: implement VK_EXT_sample_locations")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4795>

util/ra: Improve ra_set_finalize() performance.

BITSET_FOR_EACH_SET can walk a sparse set (such as a register class's set
of registers) much faster than just iterating over individual bits.

Improves freedreno startup time (as measured by shader-db ./run
shaders/closed/gputest/triangle on my x86 system) by -4.12679% +/-
1.99006% (n=151)

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4537>

util/ra: Use util_dynarray for handling the conflict lists.

Again, shortens the code significantly.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4537>

util/ra: Use util_dynarray for the adjacency list.

This make the code significantly more readable, I think (along with
shorter).  Also, using util_dynarray_delete_unordered() saves us a move of
the rest of the list when removing adjacency on a node.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4537>

util/ra: Sanity check that we're adding a valid reg to a class.

BITSET_SET might not segfault on you right away if you're just slightly
off, and an assert is nicer anyway.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4537>

util/ra: Sanity check that the driver selected a valid reg.

freedreno was returning -1 when it didn't pick a reg from the given bitset
due to an off-by-a-small-number error.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4537>

freedreno/a4xx: enable A405

This patch brings support for Adreno A405
as found on MSM8939. That chip is a cut-down
version of A4XX IP and requires no special handling.

Tested on Asus Zenfone 2 Laser (Z00T) smartphone.

Signed-off-by: Konrad Dybcio <konradybcio@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4753>

iris: handle PIPE_CAP_CLEAR_SCISSORED

this allows passing scissored clear calls through the driver where it can
be handled by a repclear shader

fix kwg/mesa#61

Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4310>

gallium: add pipe cap for scissored clears and pass scissor state to clear() hook

this adds a new pipe cap that drivers can support which enables passing buffer
clears with scissor test enabled through to be handled by the driver instead
of having mesa draw a quad

also adjust all existing clear() hooks to have the new parameter

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Vasily Khoruzhick <anarsoul@gmail.com>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4310>

i965: Use correct constant for max_variable_local_size

Fixes: 5664bd6db38 ("i965: Implement ARB_compute_variable_group_size")
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4799>

iris: move iris_vtable to iris_screen

instead of inlining this into every context, now a struct is used in the screen
struct to reduce memory usage and simplify a couple of the methods

Closes: https://gitlab.freedesktop.org/kwg/mesa/-/issues/6
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4376>

intel/fs: Don't delete coalesced MOVs if they have a cmod

Shader-db results on ICL:

    total instructions in shared programs: 17133088 -> 17133287 (<.01%)
    instructions in affected programs: 61300 -> 61499 (0.32%)
    helped: 0
    HURT: 199

This means it's likely fixing 199 bugs. :-)  All the changed shaders are
in Mad Max.  It's surprisingly difficult to get the back-end compiler to
generate a pattern that hits this we don't tend to emit a lot coalescable
MOVs.  The pattern in Mad Max that's able to hit is fsign(fsat(x)) under
the right conditions.

Closes: #2820
Cc: mesa-stable@lists.freedesktop.org
Tested-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4773>

st/mesa: expose more SPIR-V capabilities

Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4760>

mesa: report GL_INVALID_OPERATION for invalid glTextureBuffer target

This fixes:
    KHR-GL46.direct_state_access.textures_buffer_errors
    KHR-GL46.direct_state_access.textures_buffer_range_errors

Fixes: 98e64e538af - main: Added entry point for glTextureBuffer
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4759>

pan/mdg: Replicate 16-bit swizzles

We don't support vec8 quite yet anyway, this fixes dot products.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Ensure fdot is scalar out in disasm

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Move condense_writemask to disasm

The compiler should *never* use this. Packing should be 1 way.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Pass through some types from scheduling

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Don't crash on unknown branch target

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Make some branch targets more explicit

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Always print the mask

Meaningful for fp16.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Specialize swizzle to type

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>

pan/mdg: Lower specials to 32-bit

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4793>