Use vk_expand_src_stage_flags2 and vk_expand_dst_stage_flags2, instead
of vk_expand_pipeline_stage_flags2, to expand bottom-of-pipe and
top-of-pipe respectively.
Fixes: 5544d39f44 ("panvk: Add a CSF backend for panvk_queue/cmd_buffer")
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32289>
Update just enough of the fail list to have a green CI. I'm sure a
no-fraction run would uncover other improvements/failures/flakes, but
the goal here is to detect improvements/regressions introduced by new
MRs, not to make the list accurate. This will be tackled in a follow-up
MR.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32302>
Add the missing fs_user_dirty and PANVK_CMD_GRAPHICS_DIRTY_RENDER_STATE
checks.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32267>
Sort the dirty states and make it clear that we use
panvk_rendering_state.
Constify color_attachment_samples for panvk_per_arch(blend_emit_descs).
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Benjamin Lee <benjamin.lee@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32267>
There's no reason to calculate this more closely; the Vulkan spec
explicitly allows for it to be conservative. And there's no other Vulkan
driver in Mesa that currently does anything else.
But, we have another reason to limit to this specific value (which also
happens to be the minimum value allowed by the spec); we'll overflow the
32-bits of slice_stride for resources where the product of width, height
and texel-size is over UINT32_MAX. But with this limit in place, we
avoid this.
This limit will go away in v11, beacuse there's an additional five bits
of slice_stride there. But let's leave that for later.
Anyway, let's document why this is the correct limit, insted of having
the FINISHME-comment.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: John Anthony <john.anthony@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32265>
We're supposed to report an error if we're attempting to allocate images
larger than maxResourceSize. So let's add the logic for this.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: John Anthony <john.anthony@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32265>
Panvk currently enables VK_EXT_vertex_attribute_divisor, but Mali HW
does not support a non-zero firstInstance when a divisor is used.
supportsNonZeroFirstInstance is correctly set to false to advertise
this, however this property was only added when the extension was
promoted. Thus we need to remove support for
VK_EXT_vertex_attribute_divisor and enable
VK_KHR_vertex_attribute_divisor instead.
Also fixes an issue with non-zero divisor for v10.
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32137>
Make sure frag_completed is incremented once per render pass, regardless
of layer count.
This fixes
[44354.379592] panthor fb000000.gpu: [drm] Failed to extend the tiler heap
in some cases.
Fixes: 157a4dc509 ("panvk/csf: Fix multi-layer rendering")
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32234>
It doesn't feel great that we need to compile multiple identical shaders
just because we're going to toggle a bit in the command-stream, but this
seems to be the current state-of-art in mesa, so hmpf...
It makes state-validation trivial, so there's that.
This is loosely based on what NVK does.
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32004>
We already support VK_EXT_index_type_uint8 and this is the promoted
version of it.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32248>
We already have all the lowering we need for this.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32248>
Both are implemented but were not enabled.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32248>
This is also needed to properly support VK_KHR_swapchain, so we should
implement it.
Fixes: d970fe2e9d ("panfrost: Add a Vulkan driver for Midgard/Bifrost GPUs")
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32216>
This is required by VK_KHR_swapchain, so let's support it.
Fixes a crash in this CTS test-case:
dEQP-VK.wsi.wayland.swapchain.simulate_oom.image_swapchain_create_info
Fixes: d970fe2e9d ("panfrost: Add a Vulkan driver for Midgard/Bifrost GPUs")
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32216>
We updated maxImageDimension2D etc to report the actual max size, but we
forgot to update GetPhysicalDeviceImageFormatProperties in the same way.
Let's do that to make things consistent.
This fixes the following CTS test-case:
dEQP-VK.wsi.wayland.swapchain.create.image_extent
Fixes: d5ed77800e ("panvk: Fix GetPhysicalDeviceProperties2() to report accurate info")
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32221>
On modern Mali GPUs, we can have 16 bits for the X and Y sizes, already
overflowing 32-bit barrier even with a single layer of byte-sized
formats.
So let's make sure we have enough bits to avoid overflows here.
Fixes: d5ed77800e ("panvk: Fix GetPhysicalDeviceProperties2() to report accurate info")
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32221>
This will need to be set to true when the GLSL linker lowers IO, which
can later be unlowered by st/mesa, and then drivers can lower it again
without load_interpolated_input. Therefore, it can't be a global
immutable option.
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32229>
vk_common_*Wait* calls vk_device_check_status to detect device lost.
This allows device lost to be reported more timely.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32166>
When PANVK_DEBUG=sync detects a failed job, report queue lost
immediately.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32166>
Make sure the sysval is pushed.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-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/32203>
In case of nested if/else, the current block will not be the loop block.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.cim>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31843>
We were ignoring rasterization samples count before.
This fix "dEQP-VK.query_pool.occlusion_query.no_attachments_multisample"
failure.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.cim>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31843>
Panfrost doesn't support PAN_KMOD_BO_FLAG_GPU_UNCACHED and to keep
things usable on all generation, let's do that for now.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.cim>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31843>
This is supported by the hardware since v10.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32215>
We can treat VK_QUEUE_FAMILY_FOREIGN_EXT as the host, This makes sure
that, on release, all subqueues self-wait and all caches are flushed.
On acquire, all caches are invalidated.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32164>
The spec says that the user-specified srcStageMask/srcAccessMask should
be ignored for the acquire operation and the user-specified
dstStageMask/dstAccessMask should be ignored for the release operation.
Since we don't need any special handling for VK_QUEUE_FAMILY_EXTERNAL,
override them to NONE.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32164>
nir_lower_pack can generate split operations, execute algebraic again
to handle them.
This fix an assert on
"dEQP-VK.spirv_assembly.instruction.compute.opphi.vartype_float16" and
probably others tests.
Fixes: 3904cfabd6 ("bi: Use nir_opt_load_store_vectorize")
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: John Anthony <john.anthony@arm.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32131>
Handled by common code.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: John Anthony <john.anthony@arm.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32131>
Handled by common code.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: John Anthony <john.anthony@arm.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32131>
Already implemented in common code.
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: John Anthony <john.anthony@arm.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32131>
Poison all cmdbuf registers to make sure we don't inherit state from
a previously executed cmdbuf.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31911>
get_fs() (and thus fs_required()) is called enough times during a draw
that it makes sense to cache the value in the graphics state instead of
calling fs_required() repeatedly.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31911>
Keeping those distinct makes it hard to maintain (fixes hitting one
version but not the other). Let's make it common code and guard CSF/JM
specific code under #if PAN_ARCH blocks.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31911>
Coalesce all the dirty bits into a single bitset, and use dirty bits for
stuff that were already tracked through NULL GPU pointers.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31911>
When IDVS+malloc is used, there's no linking involved (getting the
VS and FS shaders to agree on the varyings attributes), so we can
purely and simply skip this phase.
If we ever have to support the non-malloc or non-IDVS case, we'll need
to revisit the linking logic anyway, so let's kill the linking on v10
for now.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31911>
We're about to bitset-based driver-internal dirty state tracking, and
we'll need to define new xx_is_dirty() macros, so let's rename the
existing one dyn_gfx_state_dirty() to avoid the confusion, and move it
to panvk_cmd_draw.h, since it's the same for JM and CSF.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31911>
