Interleave mode specified per-plane on Valhall. The texture descriptor proper
merely has a flag specifying whether planes are somehow interleaved
(u-interleaved, AFBC, or block compressed formats) or whether they are all
linear (and uncompressed).
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14851>
Flesh out the ZS/CRC XML, adding fields required for AFBC. Valhall allows AFBC
compressing stencil buffers independent of depth buffers, which is a new feature
since Bifrost. That results in a shuffling of the descriptor.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14851>
This looks superficially like the Bifrost "Surface" descriptor, but it
additionally specifies the in-memory representation of blocks (clumps). If I
understand correctly, decompression is controlled by the plane descriptor,
rather than the texture descriptor level. This is a bit more flexible than
Bifrost.
Once the new fields here are wired up to Mesa, my
dEQP-GLES2.functional.texture.* failures should go away... I hope!
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14851>
Otherwise we get DATA_INVALID_FAULT trying to run even trivial null jobs. For
each descriptor, set the correct alignment.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14851>
Removed since there's a new ABI for blend shaders. Even if we always write 0,
it's better not to pack this at all, and to denoise the dumps.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14851>
Although Bifrost clause packing and register assignment is tricky, the
relevant code is by now extensively tested, and there's no remaining
reverse-engineering here. So disassembling verbosely just adds tons of
noise to pandecode without increasing the useful information.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Suggested-by: Icecream95 <ixn@disroot.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14543>
It's a pointer to a thread storage descriptor, not a framebuffer
descriptor. Unlike Midgard, these don't have to alias. The FBD pointer
was unused anyway, so remove it to reduce noise in pandecode dumps.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14543>
Add a helper to dump all mapped GPU memory. This is a blunt, seldom
useful instrument ... but when it /is/ useful it's your only option.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14543>
Rather than emulating page tables, poorly, with a hash table, use a
red-black tree and store the intervals directly. This is deterministic
instead of probabilistic, attaining O(log n) performance for n mapped
intervals which is good enough. Unlike the hash table approach, this
allows us to iterate intervals easily.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14543>
Consider the following innocuous-looking code:
pan_merge(packed, vtx->attributes[i], ATTRIBUTE);
Under the current implementation, this code is completely broken. Why?
The current implemention is a macro which hardcodes the loop index i,
which shadows the i used to index attributes. Pull out a helper method
so we do the right thing without resulting to further preprocessor abuse
(__COUNTER__).
While making things more robust, assert the crucial pan_merge
invariant that the total size is a multiple of 4; if this fails, the
routine risks memory corruption.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14119>
Preload exactly what the shader needs, based on the compiler's mask of
uninitialized registers, rather than trying to sync pan_shader.h with
the behaviour of code gen. Would've saved me some debugging over the
years...
As a bonus this avoids preloading unnecessary registers, particularly in
compute shaders. In theory this should reduce power consumption.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154>
Valhall v9 introduces a number of new data structures since Bifrost v7,
and removes a number of traditional data structures. Add decode routines
for the new Valhall data structures, and condition the old routines on
(PAN_ARCH <= 7) to remain buildable and warning-free.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14063>
Fork the latest canonical XML (Bifrost v7) and adapt to the data
structures found in the earliest Valhall GPU I could get my hands on
(Valhall v9). This should minimize the churn needed for the port by
keeping the Valhall model close to the Bifrost we already supported.
It is not known what happened to v8. It appears to have been yeeted from
existence.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14063>
Although known fields wouldn't be given the type "hex", it is useful as
the default type for unknown fields while reverse-engineering, and as
such is used in the Valhall XML.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14063>
These kernels aren't tested (and are probably broken) elsewhere. Don't
waste cycles trying to compile for other architectures. This reduces the
amount of code that needs to be ported to a new architecture.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14064>
These flags control special CRC handling for empty tiles using the CRC
clear colour field added on Bifrost. Their use depends on CRC being
used. We missed these flags earlier; let's add them since they are used
by the Valhall DDK but are not new to Valhall.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13982>
Pattern match the point coord sysval and support lowering it as well.
This is required to handle flipped framebuffers on Bifrost. However,
what this pass normalizes to is the opposite of the hardware mode we
used on Bifrost before, so we need to swap modes at the same time to
prevent regressions.
Fixes Piglit glsl-fs-pointcoord and glsl-fs-pointcoord_gles2
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13073>
For each blend mode in our blending unit tests, add whether we can set
the alpha_zero_nop and alpha_one_store flags and check against the
predicates.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Acked-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13508>
Some Mali GPUs can avoid storing to the tilebuffer if src alpha = 0, and
can replace blending with a store if src alpha = 1. This saves power in
the common case of alpha blending. Add predicates to check if these
optimizations are valid for a given blend equation.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Acked-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13508>
Make it clear that the distinction is the facingness of the primitives
the depth bias applies to.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13509>
We need to know the internal (physical) formats used for AFBC of a given
logical format, in order to check format compatibility and determine if
we need to decompress AFBC for conformance.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13205>
According to mali_kbase, all Bifrost and Valhall GPUs are affected by
issue TSIX_2033. This hardware bug breaks the INTERSECT frame shader
mode when forcing clean_tile_writes. What does that mean?
The hardware considers a tile "clean" if it has been cleared but not
drawn to. Setting clean_tile_write forces the hardware to write back
such "clean" tiles to main memory.
Bifrost hardware supports frame shaders, which insert a rectangle into
every tile according to a configured rule. Frame shaders are used in
Panfrost to implement tile reloads (i.e. LOAD_OP_LOAD). Two modes are
relevant to the current discussion: ALWAYS, which always inserts a frame
shader, and INTERSECT, which tries to only insert where there is
geometry. Normally, we use INTERSECT for tile reloads as it is more
efficient than ALWAYS-- it allows us to skip reloads of tiles that are
discarded and never written back to memory.
From a software perspective, Panfrost's current logic is correct: if we
clear, we set clean_tile_writes, else we use an INTERSECT frame shader.
There is no software interaction between the two.
Unfortunately, there is a hardware interaction. The hardware forces
clean_tile_writes in certain circumstances when AFBC is used.
Ordinarily, this is a hardware implementation detail and invisible to
software. Unfortunately, this implicit clean tile write is enough to
trigger the hardware bug when using INTERSECT. As such, we need to
detect this case and use ALWAYS instead of INTERSECT for correct
results.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13205>
AFBC is an optional feature on Bifrost. If it is missing, a bit will be
set in the poorly named AFBC_FEATURES register. Check this so we can act
appropriately.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13497>
The number of varying records we need to reserve in the worst case is
greater than the number of source-level varyings we advertise
(gl_Position, gl_PointSize...)
We advertise MAX_VARYINGS source level varyings, which means anywhere we
manipulate varyings we need up to (MAX_VARYINGS + max non-source level
varyings) records. Add a PAN_MAX_VARYINGS define for this and use it
throughout.
Fixes a buffer overflow in Piglit glsl-max-varyings, which now passes
instead of crashes.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13070>
The number of special varyings on midgard can influence how much space
we need to allocate for varyings in the compiler ABI. Move the enum so
we can get access it.
No functional change. This is cc stable purely so the following patches
can be backported.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13070>
ASTC textures all use a common ASTC format, with the ASTC block
dimension configured with auxiliary bits at the bottom of the payload
pointer. Add the corresponding enum for ASTC 2D and 3D.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12814>
Start with the enums that were manually redefined in
pan_{texture,format}.h and the blend equation descriptors.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12208>
When the render target format is raw, the swizzle is ignored. Let's
set it to identity to avoid misleading the pandecode reader into
thinking the swizzle is applied.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Suggested-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12793>
The output swizzle defined in the render-target descriptor is ignored
when the format is RAW. In that case, we have to swap the components
when lowering FB stores/loads if we want to get the right color.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12793>
Fixes several problems in the pan_blit() logic:
1. We actually need the reciprocal of the depth scaling in z_scale (maybe
we should rename this field z_scale_rcp to make it clear)
2. When Z end < Z start we should remove one to the cur_layer/layer_offset
instead of doing it on the last_layer field, otherwise there's an
off-by-one error
3. The Z src offset should be adjusted to account for scaling. If we don't
do that we won't sample from the right layer when upscaling.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12961>
Since we have no guarantee that start < end, we can't really tell to
which one the offset applies to. Let the caller take care of that.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12961>
Oh, the irony. I linked to this file in a software design class as an
example of how unit testing works under the hood, since it's not using
any particular testing framework. In doing so I realized the test is
totally broken. It doesn't matter -- the tests passed before, pass now,
and the code being tested is correct. But let's still fix the
embarassing logic error for future Panfrost hackers.
Fixes: d42e53c77a ("panfrost: Unit test clear colour packing")
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13006>
DCD size on Bifrost is supposed to be 32 words wide, but this change
will only happen after the per-gen XML split. We have to manually append
the DRAW_PADDING for now.
Fixes: de13fdc251 ("panfrost: Prepare pandecode to per-gen XML")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12970>
The vulkan driver needs to patch job headers when re-issuing batches.
Extend pan_preload_fb() so it can return the emitted tiler jobs.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12095>
The ZS view can be NULL if a stencil-only buffer is attached to the FB.
Fixes: 1de393fec5 ("panfrost: Fix ZS reloading on Bifrost v6")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12095>
Min/max index search shaders are different for the !primitive_restart
and primitive_restart. We need to add entries for the primitive restart
cases otherwise we might retrieve a wrong shader from the cache.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12589>
In that case we should just skip the vertex/tiler jobs as done in the
direct draw path.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12589>
Do not dereference color buffer #0 in the SFBD code path if no color buffer is
attached, as with depth-only attachments. Fixes a crash running glmark2 -b
shadow on Mali T720.
Signed-off-by: Italo Nicola <italonicola@collabora.com>
Fixes: c746747cb8 ("panfrost: fix GL_EXT_multisampled_render_to_texture regression")
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12927>
So we can use this function in decode_common.c when transitioning to
per-gen XML. While at it rename the function pan_arch().
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12935>
Sampling from SCALED textures / rendering to SCALED FBOs is a bit tricky
(requires extra int <-> float conversions in a few places).
mesa/st only use SCALED formats as vertex formats, and those formats
are optional in Vulkan, so let's drop the RENDER/TEXTURE flags to keep
things simple.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Suggested-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12508>
Offical naming of Mali GPUs is like Mali-G52 or Mali-T860 wth a dash.
Also variants of the same GPU e.g. revision 1 are generally not part
of the name. This adds a dash instead of a space between Mali and the
model and also splits off the r1 revision with a space. This should
keep the naming in-line with offical names and with what the binary
DDK uses for naming.
Signed-off-by: Carsten Haitzler <carsten.haitzler@foss.arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12667>
The Vulkan driver needs to patch job headers when re-issueing a command
buffer. Return the tiler job pointer to allow that.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12552>
This can happen when one wants to obtain a mirrored view. We need
to make sure the min <= max before emitting the viewport.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12552>
This way the transition to per-gen XML files gets simpler.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12551>
The gen_macros.h header should include the common header file when
PAN_ARCH is undefined, thus making those redefinitions useless.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12551>
We will soon have per-gen pack headers. Let's rename the meson variables
to reflect that.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12551>
Include gen_macros.h instead so we can smoothly transition to per-gen
XMLs.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12551>
This way we will only have a single entry point, thus making the
transition to per-gen XML files easier.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12551>
This will ease the transition to per-arch XML files. While at it, patch
pan_cmdstream.c to use this new macro and avoid an #if section.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12551>
And replace all references to MALI_xxx_{LENGTH,ALIGN} by
pan_{size,alignment}(xxx) calls so we can give generic alias to
midgard/bifrost specific descriptors.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12551>
We already took the lock, we just unlocked too early. Since the label is
reset in the BO cache, this is racy. Minimal impact in practice but is
still /wrong/ and caught by helgrind.
Fixes: 3fa1f93dac ("panfrost: Label all BOs in userspace")
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12525>
This is a presumed erratum workaround. Fixes INSTR_INVALID_PC faults on
some draw_buffers_indexed.* cases on Midgard, where a blend shader is
required to pack RT n > 0.
Backport the workaround from the GL driver. The helper is now in common
code for panvk to use as well; it has the same bug.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11383>
So the hash function doesn't end up hashing uninitialized values.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reported-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Fixes: bbff09b952 ("panfrost: Move the blend shader cache at the device level")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11383>
Although it is passing all of dEQP-GLES31, it is failing a few
KHR-GLES31.* tests. It also has performance issues at the moment. Invert
the existing noindirect debug flag to become a indirect debug flag. Set
this flag for dEQP-GLES31 CI on G52, to make sure the code doesn't bit
rot on the hope someone will pick this up later on.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12478>
In b9c095cc2c ("panfrost: Rewrite the clear colour packing code"),
packing of clear colours was corrected to use the tilebuffer's
fractional bits, fixing dithering of the clear colour with formats like
RGB565. Unfortunately, that commit did so unconditionally. If the
framebuffer is dithered, but dithering is disabled at the time of
the clear, we would incorrectly dither the clear.
This is a regression, as the old (broken) code passed the relevant CTS
test. What's the catch? Depending on dither state, there are two
formulas to pack tilebuffer colours. We need to handle both. Fixes
KHR-GLES31.core.draw_buffers_indexed.color_masks.
Fixes: b9c095cc2c ("panfrost: Rewrite the clear colour packing code")
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12460>
There is a dependence on dithering state about which I was previously
unaware. All these test cases were with dithering enabled, so mark that
down.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12460>
dEQP has poor coverage of clear colours with odd formats, and doesn't
check that we dither as expected. This functionality is trivial to unit
test, so there's no excuse not to. Nontrivial reference values are
captured from pandecode of the Mali G52 DDK but should be valid for all
Midgard/Bifrost.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12365>
We support B5G6R5 as blendable, this is just a swizzle away. Reduces the
amount we hit blend shaders, and will fix a clear colour packing unit
test in a moment.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12365>
At the beginning of a render pass, the hardware will fill the tilebuffer
with an arbitrary 128-bit word. To implement colour clears, the driver
must pack the API-specific clear colour according to the 128-bit layout
of the tilebuffer. This layout depends only on the render target format.
The existing code to handle this was based on loose guesswork. It works
for the format / clear colour combinations tested in dEQP-GLES3, but it
is severely deficient in the general case. It works by matching on the
PIPE format of the render target (not the layout of the tilebuffer). For
special cased PIPE formats, it open codes a buggy pack routine.
Otherwise, it defaults to util_pack_color in the hope that will work.
Since util_pack_color doesn't know anything about Mali tilebuffer
layouts, that means it's defaulting to wrong behaviour.
Now that we understand internal tilebuffer layouts, let's rewrite the
packing code. Instead of matching PIPE formats, map the PIPE format to
the internal tilebuffer layout using the common table, ensuring the
mapping remains in sync with the render target descriptor. Then for
blendable tilebuffer formats, pack using a common float -> fixed point
path supporting optional sRGB translation. Raw formats use
util_pack_color as before.
For formats with less than 8 bits per channel, the new code uses the
fractional bits of the fixed-point representation. This is required for
correct dithering if the clear colour is not exactly representable in
the final low precision format.
In summary, at least the following bugs in the old code are fixed:
* Swapped R/B channels with sRGB
* Swapped R/B channels with some missing formats
* Incorrect dithering with RGB565, RGB5_A1
Fixes the following test cases:
dEQP-EGL.functional.wide_color.window_8888_colorspace_srgb
dEQP-EGL.functional.wide_color.pbuffer_8888_colorspace_srgb
dEQP-EGL.functional.wide_color.window_888_colorspace_srgb
dEQP-EGL.functional.wide_color.pbuffer_888_colorspace_srgb
Later in the series, unit tests are added for the new implementation.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12365>
Transfer ownership of the render node fd to the panfrost_device (minor
change to panvk), and then close the file descriptor for the render node
bound to the panfrost_device when destroying the panfrost_device. Of all
the users of panfrost_open_device, panvk is the only one that correctly
closed the fd before. Accordingly, this fixes an fd leak in the Gallium
driver (and performance counter utilities).
This fix still applies to the Gallium driver when renderonly is in use--
although renderonly closes its own fd, the fd is _duplicated_ in
panfrost_drm_winsys.c, so renderonly and panfrost must _both_ close
their respective fd to fix the leak.
This fixes a crash when running dEQP-EGL for more than two hours.
dEQP-EGL creates a new screen for every test case and then immediately
destroys it. If destroying a screen leaks the fd, this causes the number
of open file descriptors to increase monotonically until the process
ends. This will eventually hit the system limit for number of open files
and abort the process.
This bug was identified while attempting to run the OpenGL ES
conformance tests via cts-runner, and then confirmed with `lsof`. With
the fix, the number of file descriptors reported by `lsof | wc -l` is
now constant while running dEQP-EGL as expected.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12346>
Bifrost adds a value for the C factor equaling 2*src. This does not
correspond directly to API blend modes so it is not too useful in
general. However, it's required for src*dest + dest*src blending to be
done in hardware instead of a blend shader. GFXbench uses that blend
mode, so it must be important ;-)
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12152>
Add unit tests for the fixed-function blending helpers in pan_blend.c.
Each test consists of a Porter-Duff blend mode and the associated
hardware state. In this commit, we add tests for the most common modes.
For motivation, this code has NOT been properly tested in CI. True,
functional correctness of the blend module as a whole is tested by
dEQP-GLES3.functional.fragment_ops.blend.* among other integration
tests. However, this testing is insufficient to check for regressions.
Crucially, the following broken patch would clear CI:
bool pan_can_fixed_function(...) {
return false;
}
In that case, blend shaders are used 100% of the time, which will
regress performance horribly but still pass dEQP. The only clue
something went wrong would be some traces changing checksum due to the
fixed-function blender producing slightly different output than
equivalent blend shaders. By unit testing the fixed blend path, we
ensure we always use the fixed-function path when we expect it to.
Similarly, using incorrect values for the blend metadata may not affect
functional correctness but will increase power consumption. Let's check
all the data we export to drivers.
Note: due to additive commutativity, there are many pairs of equivalent
Mali blend modes. Unfortunately, the vendor is... inconsistent about how
to resolve ambiguous modes. Our algorithm for computing modes is
correct; the "preferred" values are left in comments since otherwise our
tests fail despite correct code. I want to blame Bifrost for this, but
Midgard was patient zero.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12152>
This is required to disable dithering on a per-draw basis when OPAQUE
output is used (bypassing the blender which normally uses the
round_to_framebuffer_precision flag to do the same).
This functionally reverts:
ebc07f4b2f ("panfrost: Remove padded unorm blendable formats")
fae90a7940 ("panfrost: Always pick dithered tb formats")
while adding the functionality to make them useful.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12152>
If we return inside a pan_pack() the descriptor packing doesn't happen.
Cc: mesa-stable
Fixes: 8ba2f9f698 ("panfrost: Create a blitter library to replace the existing preload helpers")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12239>
This is safer, since it allows the thing being concatenated to itself be
an expande macro, which we'll use as a stopgap to construct tiler jobs
with unified code. It's also a bit more readable, I think.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11851>
Midgard calls this nearest but Bifrost calls it point sample. Of the
two, nearest is the standard term, so change the Bifrost XML to use that
name. That way we can share more code constructing samplers.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11851>
Tells you how much use Mali T720 gets that nobody noticed but
Icecream95...
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reported-by: Icecream95 <ixn@disroot.org>
Acked-by: Icecream95 <ixn@disroot.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12027>
This was useful when panvk was being bootstrapped, allowing the blitter
to be tested against a known-working driver. With panvk in-tree, I don't
see a compelling reason to keep pan_blitter support wired in but
off-by-default. Keeping it will complicate the GenXML change we're about
to make.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11785>
This allows us to unify the midgard and bifrost tables and just #ifdef
the differences. It will soon also allow us to fix a bunch of enums and
specialize blendable formats.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11785>
This will become the home for little GenXML-aware helpers, suitable to
be #include'd from pan_cmdstream.c (or panvk equivalent).
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11785>
Bifrost has a new type of job called 'index-driven vertex', which takes
in two shaders. The primary shader, called for all values, performs
position shading to a cacheline-aligned attribute buffer. The secondary
shader, called for values still live after culling, performs varying
shading.
It is the responsiblilty of the implementation to ensure that vertices
from different instances do not share a cacheline.
Signed-off-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11413>
This commit adds the actual implementations, allowing to diverge while
still sharing code that depends on pool functionality.
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Suggested-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11695>
The Gallium and Vulkan drivers will soon use different memory pool
implementation, but some pieces in libpanfrost depend on pan_pool. Let's
split the implementation so we have common bits still available while
letting the drivers implement what really matters: the allocation logic.
All the generic pieces are prefixed pan_pool, and what will become the
gallium implementation is prefixed panfrost_pool. We'll then duplicate
the panfrost_pool bits in panvk and prefix it with panvk_pool, and
implementations will start diverging from there.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11695>
Pass a memory pool to pan_blit_ctx_init() instead of creating a new pool.
Useful for Vulkan since the descriptor pool is at the command buffer
level and is thus shared by all blit batches. Doing this will save us a
BO ownership transfer.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11695>
In the vulkan driver we need to patch job headers when re-submitting
an already submitted batch. Change panfrost_scoreboard_initialize_tiler()
prototype to allow that.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11139>
Instead just group the fields about validity into a simpler structure in
panfrost_resource. Panvk can do the same. Common code shouldn't be
thinking in terms of this 'larger' structure anyway.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
Job type is alone with bitsize in the bottom byte of the addressed
worse, so if we use an 8-bit store we avoid the RMW complexity.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
In actuality, this just shadows the crc_valid for pan_cs... the
data_valid checks are contained in the caller and just add noise.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
CRC is intended for final render targets and especially for UI, not the
kind of things you'd mipmap. Meanwhile CRC only works for a single
level, meaning at any given point, half the CRC buffer would be wasted
for a full miptree.
"Arm Mali Best Practices Guide" tells developers that the DDK only
enables CRC for non-mipmapped resources (at least the Vulkan DDK), so
let's do the same, save some memory, and simplify our code.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
Technically we can stick the offset in the vertex ID attribute record,
but this is a faster way to get the test passing and Midgard perf?
what's that?
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
You'd just get a blend shader anyway, and since they're not spec
requirements, let's not worry about backporting the Midgard lowerings.
Takes dEQP-GLES31.functional.fbo.color.tex2d.* on Midgard from crashing
to not supported.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
Since the GLSL compilers will pack together flat varyings with no regard
to type, under the assumption the backend can deal with it. I guess we
can deal with it then... Fixes fails in
dEQP-GLES31.functional.separate_shader.random.*
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
Instead of doing a complicated hack with the POT divisor, just zero the
stride of the linear attribute buffer like we do on the CPU.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>
The function is complicated enough as it is -- hide the bit twiddling
behind a helper function.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11123>