We want to be able to survive accesses to, from Vulkan's
perspective, unmapped regions of sparse resources. For that we
allocate a single page -sized bo, which we'll use to implement
sparse unmapping by mapping the address range to this bo.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35287>
Priority values will be used later one when creating job contexts.
Reviewed-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Ashley Smith <ashley.smith@collabora.com>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37075>
In the bi_emit_load_attr call site, we can use the imm_index value even
if the function returns false. The bifrost path handles this correctly.
Fixes: 652e1c2e13 ("pan/bi: Rework indices for attributes on Valhall")
Signed-off-by: Olivia Lee <olivia.lee@collabora.com>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37464>
Previously we were passing the original compile inputs, rather than the
variant-specific inputs. No actual bugs are caused by this because we
don't use the variant infrastructure for anything yet.
Fixes: ff9907927f ("panvk: Add basic infrastructure for shader variants")
Signed-off-by: Olivia Lee <olivia.lee@collabora.com>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37463>
We do not support VK_EXT_shader_object so far but vk_shader layer
depends on those values so we should fill them.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37452>
We now set fb_fetch_output and fb_fetch_output_coherent to be consistent
with nir_lower_io.
This has no impact in general unless some generic pass depends on those
infos.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37452>
It does not look like our custom version has anything special to offer.
Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Acked-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37421>
Advertise the extensions without VK_TIME_DOMAIN_DEVICE_KHR support is
not very useful.
Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Acked-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37421>
To lower 64bit sources we emit a COLLECT -> SPLIT pair to force
allocation into consecutive registers. When the sources for COLLECT
are outputs of the same SPLIT already, we can omit the COLLECT + SPLIT
pair.
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Aksel Hjerpbakk <aksel.hjerpbakk@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37398>
Use sequence-scoped clock (64 <= ID < 128) for GPU clock because there's
no central daemon emitting consistent snapshots for synchronization
between CPU and GPU clocks on behalf of renderstages and counters
producers.
When CPU clock is the same with the authoritative trace clock (normally
default to CLOCK_BOOTTIME), perfetto drops the non-monotonic snapshots
to ensure validity of the global source clock in the resolution graph.
When they are different, the clocks are marked invalid and the rest of
the clock syncs will fail during trace processing.
Now that PanVK has switched to use CLOCK_MONOTONIC_RAW CPU clock, here
we make the GPU clock sequence-scoped so that clock sync for all the
trace packets emitted with the same trusted_packet_sequence_id will be
done in an isolated manner (basically perfetto makes each scoped GPU
clock globally unique).
Meanwhile, since the clock is now sequence-scoped (unique per producer +
writer pair within the tracing session), we can simply pick 64 to start
with, and later extend to support multi-gpu (offset with primary minor).
Fixes: e278a89fdd ("panvk/perfetto: improve clock synchronization using CLOCK_MONOTONIC_RAW")
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37355>
VK_DEPENDENCY_ASYMMETRIC_EVENT_BIT_KHR makes vkCmdSetEvent2 behaves like
vkCmdSetEvent, let's handle that appropriately.
This fixes failures on VKCTS main with
"dEQP-VK.synchronization2.op.single_queue.event.*_maintenance9".
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Fixes: b8ccbc414a ("panvk: enable KHR_maintenance9")
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37396>
Those are new tests present on current VKCTS main and that are also part
of waivers.xml.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37396>
This might be a bit overly careful, but it seems like a good idea to use
both mechanisms to avoid accidental symbol leakage. I also don't think
it matters much in practice, because all sane applications use the the
Vulkan loader, and that shouldn't forward these symbols anyway.
While we're at it, let's wire up a test so we notice if this stops
working.
Acked-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37371>
This allows us to avoid accidental feature regressions, by verifying
that the reality matches the expectations in CI.
This is inspired by a similar change in r300.
Acked-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37363>
It allows us to use AFBC even if separateDepthStencilLayouts=true.
Unfortunately, AFBC(S8) is only supported on v9+, so we keep using
interleaved Z24S8 on earlier gens.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
panvk_image_can_use_afbc() doesn't know about depth/stencil format
lowering, and does the AFBC format check on the wrong format if planar
depth/stencil is enabled. Inline what we need from this helper in
panvk_image_can_use_mod(). Ultimately we should make it so that
panvk_image_can_use_afbc() uses panvk_image_can_use_mod() and not the
other way around.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
We're going to support Z24S8 planar images, but only on v9+. Let's
pass an image to panvk_plane_index() so we can extract the stencil
plane index from the number of planes instead of basing it only on the
format.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
We are about to use it at initialization time, so let's make sure it's
initialized as early as possible. We defer the initialization to a helper
because we will extend it to support planar Z24S8.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Only works on Valhall for now.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Use AFBC when we can.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
We can't have separate depth/stencil layouts with Z24S8, so make sure
we always use a linear layout in that case.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Non-UNORM/non-RGBA8 formats forces blend shaders to be used when the
graphics pipeline is involved. We also have a few formats that can't
be used with AFBC, so let's consolidate the formats we pick when using
a graphics pipeline independently of the image modifier.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
All the meta stuff is per-gen anyway, and there's nothing in
pan_device.h needing the stuff defined in panvk_meta.h, so let's
just make this file per-gen, which will allow us to use PAN_ARCH in
the inline helpers.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
We can't create texture descriptors with a format that's different
from the image format, because the texture format encodes the
compression mode on Bifrost. So let's forbid AFBC when
VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT is set.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Thanks to the decorrelation of compression mode and texture format,
AFBC is type-agnostic on v9+. We can thus safely allow UINT, SINT and
SNORM variants. The FLOAT variants are still not supported though.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
AFBC(RAW24) is not supported on v9+. Use RAW32 instead, and let the AFBC
compression mode select the actual size.
No Fixes tag here, because AFBC(RAW24) is not a thing until we allow
non-UNORM formats with AFBC.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
One we have selected a pan_afbc_mode (AKA AFBC format) for an image,
there's no reason for it change, so let's cache that at the
pan_image_layout level and re-use it when we can instead of doing
the pipe format -> afbc mode conversion over and over again.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Pass a pan_image_usage object to pan_image_test_props() and do the mod
selection in two passes: one where we only accept optimal modifiers,
and if none was found, a second pass to pick a non-optimal one.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
AFBC(Z32) has always been supported through AFBC(RGBA8), the entry was
just missing. AFBC(S8) on the other hand, is something that has been
added to v9.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Mapping Z32_FLOAT to R32F works fine until we start using AFBC(Z32),
which triggers DATA_INVALID faults. That's not an issue on v9+
because the compression mode and texture format are decorrelated,
but we need this change if we want to support AFBC(Z32) on v7.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Testing if a modifier is supported for a set of image properties is not
enough when we're supposed to pick the best modifier among a selection
of modifiers. Extend the image/mod logic to report if a modifier is
optimal when supported.
This forces us to pass extra usage information through a new
pan_image_usage object. When this usage info is missing (NULL), the
mod layer assumes a set of usage that would make the modifier optimal.
Note that the usage info also allows us to reject a few more cases
that would otherwise need to be checked by the frontend.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
The AFBC mode describes the mode of the plane-format, which is what is
stored in memory, not the image view format (which is the
interpretation of the *decompressed* memory).
This requires us to move the special S8 cases to a separate
pan_afbc_decompression_mode() helper, since those are
decompression-only mode which we need to view Z24S8 (AKA RGBA8)
as X24S8, or R8 as R8R8. While at it, get rid of PAN_AFBC_MODE_S8,
since it's not a thing in practice.
No Fixes or Cc-stable tag here, because things were working just
fine before that in the gallium driver, and AFBC is still an opt-in
feature in panvk.
Closes: https://gitlab.freedesktop.org/panfrost/mesa/-/issues/205
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
We need to add a JM barrier after the memset(0) COMPUTE job if we want
to ensure the header reset happens before any texturing from this texture
in subsequent COMPUTE/VERTEX jobs.
Fixes: c95f899305 ("panvk: add a meta command for transitioning image layout
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
cmd_clear_afbc_metadata() might be called before any other job, and it's
assuming dispatch_precomp() doesn't fail in that case. We could
explicitly open the batch in cmd_clear_afbc_metadata(), but checking for
cur_batch==NULL and opening a new batch seems to be okay too, and it
allows us to not special case for v7 in cmd_clear_afbc_metadata().
Fixes: c95f899305 ("panvk: add a meta command for transitioning image layout")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
There seems to be cases where we end up with a depth/stencil preload,
with no draw associated to it, so let's make sure we preload in that
case, otherwise we will write invalid data back.
Fixes: 0bc3502ca3 ("panvk: Implement a custom FB preload logic")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
In panvk_vX_cmd_meta.c, panvk_plane_index() is passed the bit position
instead of an aspect in a couple places.
Fixes: c95f899305 ("panvk: add a meta command for transitioning image layout")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
Commit 33eff977f6 ("panvk: Use pan_image_test_props() to do our
modifier check") removed the checks that are already done by
pan_image_test_props() from panvk_image_can_use_afbc(), but it didn't
account for the fact panvk_image_can_use_afbc() is also used to
report suboptimal setup when HOST_TRANSFER is set.
Reported-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Fixes: 33eff977f6 ("panvk: Use pan_image_test_props() to do our modifier check")
Closes: https://gitlab.freedesktop.org/panfrost/mesa/-/issues/204
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37158>
It seems like everything involving the multithreaded ES2 tests is prone
to flaking out with a segfault. Just wildcard the lot until we can
bottom out what's actually going on.
Signed-off-by: Daniel Stone <daniels@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37305>
The current code assumes 2M and 4k pages. If an allocation request
is larger than 2M, allocation will be aligned to 2M, otherwise to
4k.
The new code is informed by pgsize_bitmap. The allocation is
aligned to a particular page boundary, if the request is at least
as large as that page boundary. Note that given
pgsize_bitmap = PGSIZE_4K | PGSIZE_2M
2M requests will now be aligned to a 2M boundary, rather than 4k,
which is the case with the current code.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37288>
This function returns the page size of the VM that we're using. The
GPU page size might be different from what the host process uses.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37288>
pgsize_bitmap specifies the page sizes supported by the VM.
Aligning the mappings to huge-r pages can increase access perf.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37288>
When the host process is 32-bit, size_t can not express all of the
device address space. Note that there's still a lot of code that
uses size_t for device sizes remaining. Cleaning that up is left
for future MRs.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37288>
