The DDMADT instruction of PDS has out-of-bound test capability, which is
used for implementation of robust vertex input fetch.
According to the pseudocode in the comment block before the "LAST DDMAD"
mark in pvr_pipeline_pds.c, the check is between
`calculated_source_address + (burst_size << 2)` and `base_address +
buffer_size`, in which the `burst_size` seems to correspond to the BSIZE
field set in the low 32-bit of DDMAD(T) src3 and the `buffer_size`
corresponds to the MSIZE field set in the DDMADT-specific high 32-bit of
src3. As the calculated source address is just the base address adds the
multiplication result (the offset), the base address could be eliminated
from the check, results in the check between `offset + (BSIZE * 4)` and
`MSIZE` .
Naturally it's expected to just set the MSIZE field to the buffer size.
In addition, as the Vulkan spec says "Reads from a vertex input MAY
instead be bounds checked against a range rounded down to the nearest
multiple of the stride of its binding", the driver rounds down the
accessible buffer size before setting MSIZE to it.
However when running OpenGL ES 2.0 CTS, two problems are exhibited about
the setting of the size to check:
- dEQP-GLES2.functional.buffer.write.basic.array_stream_draw sets up a
VBO with 3 bytes per vertex (RGB colors and 1B per color) and 340
vertices (results in a buffer size of 1020 = 0x3fc). However as the
DMA request size, which is specified by BSIZE, is counted by dwords,
3 bytes are rounded up to 1 dword (which is 4 bytes). When the bound
check of the last vertex happens, the vertex's DMA start offset is
0x3f9, so the DDMADT check happens between 0x3fd (0x3f9 + 1 * 4) and
0x3fc, and indicates a check failure. This prevents the last vertex,
which is perfectly in-bound, from being properly fetched; this is
against the Vulkan specification, and needs to be fixed.
- dEQP-GLES2.functional.vertex_arrays.single_attribute.strides.
buffer_0_32_float2_vec4_dynamic_draw_quads_1 sets up a VBO with a size
of 168 bytes, and tries to draw 6 vertices (each vertex consumes 2
floats (thus 8 bytes) of attribute) with a stride of 32 bytes using
this VBO. Zink then translates the VBO to a Vulkan vertex buffer bound
with size = 168B, stride = 32B. Here the optional rule about rounding
down buffer size happens in the current PowerVR driver, and the
checked bound is rounded down to 160B, which prevented the last
vertex's 8B attributes to be fetched. It looks like this kind of
situation is considered in the codepath without DDMADT, but omitted
for the codepath utilizing DDMADT for bound check.
So this patch tries to mimic the behavior of DDMADT when setting the
MSIZE field of it to prevent false out-of-bounds. It first calculates
the offset of the last valid vertex DMA, then adds the DMA request size
to it to form the final MSIZE value. With the code calculating the last
valid DMA offset considering the situation of fetching the attribute
from the space after the last whole multiple of stride, both problems
mentioned above are solved by this rework.
There're 99 GLES CTS testcases fixed by this change, and Vulkan CTS
shows no regression on `dEQP-VK.robustness.robustness1_vertex_access.*`
tests.
Fixes: 4873903b56 ("pvr: Enable PDS_DDMADT")
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Ella Stanforth <ella@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40528>
This memory padding is enforced by GetBufferMemoryRequirements2 and
might be then checked against to decide whether it's enough.
Move it to pvr_buffer.h for further assertions.
Backport-to: 25.3
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Ella Stanforth <ella@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40528>
Currently the size of single components inside one attribute is saved
and checked against when checking DMA capability. However, the vertex
attribute DMA happens for a whole attribute instead of individually for
its components, so checking against the component size is useless -- the
size of the whole attribute is what needs to be saved and checked.
Rename all component_size_in_bytes fields to attrib_size_in_bytes, and
save the size of the whole attribute inside them.
Fixes: 8991e64641 ("pvr: Add a Vulkan driver for Imagination Technologies PowerVR Rogue GPUs")
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Ella Stanforth <ella@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40528>
The ddmadt_oob_buffer_size structure to be filled is named
`obb_buffer_size`, which is obviously a typo.
Change to `oob_buffer_size` to fix the typo.
Fixes: 8991e64641 ("pvr: Add a Vulkan driver for Imagination Technologies PowerVR Rogue GPUs")
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Ella Stanforth <ella@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40528>
Even if a linear image isn't created with usages declaring PBE writes,
the image might be exported and then re-imported with a usage that
allows rendering to.
Always align linear images' width for being written by PBE.
This fixes WSI creating surfaces with odd width, exporting them and
re-importing for rendering.
Backport-to: 26.0
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40250>
Currently the display FD is opened twice because of pvr_winsys_create()
being called twice, however the WSI (which will do modeset on the
display FD in case of VK_KHR_display) is registered against the winsys
created at PhysicalDevice enumeration time, and the display FD opened at
Device creation time will only be used for allocating dumb buffer (which
does not require master privilege).
Add a parameter to pvr_winsys_create() to indicate whether the master
privilege is desired on the display FD, and pass true only when creating
the winsys for PhysicalDevice initialization.
Fixes VK_KHR_display operation on PowerVR driver, which is broken after
the WSI code starts to drop master in commit 870e233ca5
("vulkan/wsi/display: Avoid holding drm master for the device's fd.").
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/15161
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40640>
The s0abs bit in the encoing of fred instruction is wrongly set to the
status of .neg modifier instead of .abs modifier.
Fix this copy-n-paste error.
Fixes GLCTS tests when running on top of Zink:
dEQP-GLES2.functional.shaders.random.trigonometric.vertex.4
dEQP-GLES2.functional.shaders.random.trigonometric.vertex.45
dEQP-GLES2.functional.shaders.random.trigonometric.fragment.4
dEQP-GLES2.functional.shaders.random.trigonometric.fragment.45
Fixes: 8ec174b3f9 ("pco: add support for various selection, complex, trig ops")
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40611>
In pvr_pipeline_pds.c, there's a pseudocode snippet describing the
behavior of DDMADT PDS instruction, which seems to be copied from some
internal document about PDS behavior.
However, the pseudocode isn't properly indented, especially some
brackets are misaligned. This blocks fluent reading of the pseudocode
and may even mislead the reader.
Re-indent the pseudo code with similar rules with C codes in the driver.
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Acked-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40533>
Move options were bit or-ing from the wrong enum, causing undefined
behaviour when the number of intrinsics changed.
Replaced it with the values from the right nir_move_options enum that
were previously working. (Further refinement needed on these after
extensive testing.)
Fixes: f1b24267d2 ("pco: rework nir processing and passes")
Signed-off-by: Radu Costas <radu.costas@imgtec.com>
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40568>
_mesa_sha1_format has a few remaining uses, so it's moved to build_id.c,
which is its last user.
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40383>
The old calculation depended on the sample count, and gave subpar
results for 8x MSAA with standard sample locations. The new calculation
is based on the Intel pass, with some changing of the constants so that
the sample count is always proportional to alpha for 2xMSAA and 4xMSAA
and the addition of rotating the sample mask based on the pixel.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39335>
Its no longer an error for depth and stencil formats to have invalid
accumulator format.
Fixes the following tests:
* dEQP-VK.api.info.image_format_properties.2d.optimal.d16_unorm
* dEQP-VK.api.info.image_format_properties.2d.optimal.d24_unorm_s8_uint
* dEQP-VK.api.info.image_format_properties.2d.optimal.d32_sfloat
* dEQP-VK.api.info.image_format_properties.2d.optimal.d32_sfloat_s8_uint
* dEQP-VK.api.info.image_format_properties.2d.optimal.s8_uint
* dEQP-VK.api.info.image_format_properties.2d.optimal.x8_d24_unorm_pack3
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Acked-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40456>
When the first attachment is assigned to a tile buffer, the buffer
alloc mask was not been updated. This means when a second attachment
is added to the same tile buffer it will be assigned the same offset
as the first which will lead to incorrect behaviour.
Fixes for depq-vk:
dEQP-VK.renderpasses.dynamic_rendering.complete_secondary_cmd_buff.suballocation.attachment.4.568
dEQP-VK.renderpasses.dynamic_rendering.complete_secondary_cmd_buff.dedicated_allocation.attachment.4.568
dEQP-VK.renderpasses.dynamic_rendering.primary_cmd_buff.suballocation.attachment.4.568
dEQP-VK.renderpasses.dynamic_rendering.primary_cmd_buff.dedicated_allocation.attachment.4.568
Fixes: a7de9dae6b ("pvr: Add routine for filling out usc_mrt_setup from dynamic rendering state")
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Acked-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40456>
Do not assume that the application always provides images for backing
attachments. The app can provide a super set of attachments of which
only some are actually backed with images.
We want to filter-out attachments that aren't meaningful for rendering
or sampling, and create compiler resources only for relevant ones.
Fix assert in CTS:
pvr_arch_mrt.c:215: pvr_rogue_init_usc_mrt_setup: Assertion `att_format != VK_FORMAT_UNDEFINED' failed.
Seen in pipeline monolithic, for instance:
dEQP-VK.pipeline.monolithic.multisample.misc.dynamic_rendering.multi_renderpass.r8g8b8a8_unorm_r16g16b16a16_sfloat_r16g16b16a16_sint_d32_sfloat_s8_uint.random_127
Fixes: d549c1d045 ("pvr: add pipeline handling to use dynamic rendering info")
Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Acked-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40456>
Expose the routine in preperation for a later commit.
Backport-to: 26.0
Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Acked-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40456>
Use the valid/input coverage masks for tile buffer store coverage masks
when running single/multi-sampled fragment shaders respectively.
Fixes: 297a0c269a ("pvr, pco: tile buffer support")
Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reported-by: Nick Hamilton <nick.hamilton@imgtec.com>
Acked-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40456>
The runtime builds a final pipeline state with pointers to structures
coming from the associated pipelines libraries.
So far it has considered that the viewMask was part of a structure
together with the rest of the renderpass information. This information
can be specified in pre-raster, fragment & color-output state groups
and it was assumed would be consistent for all 3. And the runtime
currently takes the pointer to the structure from the last pipeline
library (color output).
Some coming spec/cts will clarify that the viewMask only needs to be
specified for pre-raster & fragment groups, making the value in the
color-output group untrustworthy.
This change creates a new state structure to hold the viewMask on its
own so it is only gather on pre-raster & fragment groups.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com> (radv)
Reviewed-by: Aitor Camacho <aitor@lunarg.com> (kosmickrisp)
Reviewed-by: Connor Abbott <cwabbott0@gmail.com> (turnip)
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com> (v3dv)
Reviewed-by: Frank Binns <frank.binns@imgtec.com> (powervr)
Acked-by: Erik Faye-Lund <erik.faye-lund@collabora.com> (panvk)
Royaled-yes-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com> (lavapipe)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39940>
Replace loop with macros
Rewrite channel op to multi channel select to avoid extra swizzle
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Signed-off-by: Radu Costas <radu.costas@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40320>
Add checks for integer coordinates and array indexing HW features
Features require HW support and the PCO_DEBUG env var to contain the
adv_smp entry
Integer coordinates are supported for images and textures without an LOD
setting
Array indexing is not supported and will trigger an abort
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Signed-off-by: Radu Costas <radu.costas@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40139>
This structure is handled instead of ignored, so the warning shouldn't
be printed.
Supress the warning when this structure is found.
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40164>
This commit adds support for VK_KHR_maintenance4 extension by
implementing the required function.
Makes the following tests to pass/be supported:
dEQP-VK.api.info.get_physical_device_properties2.features.maintenance4_features
dEQP-VK.api.info.vulkan1p3_limits_validation.khr_maintenance4
dEQP-VK.api.device_init.create_device_unsupported_features.maintenance4_features
dEQP-VK.memory.requirements.create_info.buffer.regular
dEQP-VK.memory.requirements.create_info.image.regular_tiling_linear
dEQP-VK.memory.requirements.create_info.image.regular_tiling_optimal
dEQP-VK.memory.requirements.create_info.image.transient_tiling_linear
dEQP-VK.memory.requirements.create_info.image.transient_tiling_optimal
Signed-off-by: Leon Perianu <leon.perianu@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39776>
With VK_KHR_maintenance4, the interface matching rules are relaxed to
allow emitted vs outputs > used fs inputs; unused I/O is typically
discarded during linking, but there are some cases with more complex
types that are currently missed, such as in
dEQP-VK.pipeline.monolithic.interface_matching.vector_length.out_ivec4_in_ivec3_member_of_array_of_structures_in_block_vert_out_frag_in
This change downgrades the assertion to a warning until the linker is
amended to handle these cases.
Signed-off-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39776>
Among all subcommands, only gfx subcommands are bound to a query pool,
other subcommands seem to need no special handling.
In addition, if a ResetQuery is done before BeginQuery, the last
subcommand will be a event one, which fails the current assert that
assumes it's a gfx one.
Change the assertion of the subcommand being a gfx one to an addition
check of whether the subcommand is a gfx one.
This fixes crash of Vulkan CTS 1.4.5.1 test
dEQP-VK.query_pool.discard.normal.no_depth.none.discard .
Backport-to: 26.0
Signed-off-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39753>
Format extraction moved to separate function
Removed some magic numbers
Signed-off-by: Radu Costas <radu.costas@imgtec.com>
Reviewed-by: Simon Perretta <simon.perretta@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40067>
This test has been reported failing by Mesa CI at 8f4de30d.
However it was seen passing and randomly failing in manual
testing, so mark it as a flake.
Signed-off-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Acked-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40117>
- RGBA8888_* is a preprocessor alias for R8G8B8A8_* in u_format.yaml.
- Both entries in the format tables collide on the same enum value, and
RGBA8888 overwrites R8G8B8A8.
- The fix was reverting to the version that was in the commit
39e949434c because there is a different format
was used that did not cause any collisions.
dEQP fixes:
dEQP-VK.api.info.format_properties.r8g8b8a8_sint
dEQP-VK.api.info.format_properties.r8g8b8a8_snorm
dEQP-VK.api.info.format_properties.r8g8b8a8_uint
dEQP-VK.api.info.format_properties.r8g8b8a8_unorm
Fixes: 9f740b26a6 ("pvr: Fix bugs in the format table")
Signed-off-by: Leon Perianu <leon.perianu@imgtec.com>
Tested-by: Icenowy Zheng <zhengxingda@iscas.ac.cn>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40038>
On the Rogue architecture add support for using a fragment passthrough
shader when there is no fragment shader present in a graphics
pipeline but the sample mask is required.
fix:
dEQP-VK.pipeline.monolithic.empty_fs.masked_samples
Backport-to: 26.0
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Co-authored-by: Simon Perretta <simon.perretta@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40048>
Configure the EOT setup for SPM EOT programs so that the generated
programs load the tile buffer into the output buffer before doing
the emit
Partial fix for:
dEQP-VK.renderpass.*.attachment_allocation.input_output.71
Backport-to: 26.0
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40002>
In subpasses preserve attachments are not used by the subpass but
their contents must be preserved throughout the subpass.
Add a list for the preserve attachments info specified by a subpass
and when determining a subpass attachments total uses check the
preserve attachments list and add it uses to the total.
Partial fix for:
dEQP-VK.renderpass.*.attachment_allocation.input_output.71
Backport-to: 26.0
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40002>
The struct will also be used for preserve attachments in the next
commit.
Backport-to: 26.0
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40002>
