fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-06 11:38:05 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
146501 commits 66 branches 933 tags 1,015 MiB
Commit graph

146501 commits

This branch
This branch
All branches
Author SHA1 Message Date
Mike Blumenkrantz
86b24fba05 zink: align pipe_resource and sampler_view allocations to cachelines 
this eliminates false sharing for atomics

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13431>
 2021-10-19 02:40:37 +00:00
Mike Blumenkrantz
89ed9ed400 zink: don't ralloc zink_resource structs 
the hash tables can just have their own contexts and be freed explicitly

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13431>
 2021-10-19 02:40:37 +00:00
Mike Blumenkrantz
4cad3da409 lavapipe: clamp attachment clear rect sizes 
this is a spec violation, but crashing isn't cool, so do a little clamping

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
67dd6b9f0f lavapipe: pull layer count from render state during resolve 
vk_framebuffer may be null

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
f25a98318b lavapipe: remove lvp_subpass::has_color_att 
unused

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
f7e9500dc2 lavapipe: simplify some attachment derefs 
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
d914df72ab lavapipe: store subpass directly to rendering_state 
this is fewer array derefs

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
a0c81efcf4 lavapipe: remove last VK_ATTACHMENT_UNUSED check 
these are all just null checks now

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
58e18a2be9 lavapipe: remove lvp_subpass_attachment and use lvp_render_pass_attachment refs 
this is one fewer indirect reference that allows removing a bunch of stuff from
renderpass creation

now also unused subpass attachments are just NULL pointers, making detection simpler

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
5e3bc8b18d lavapipe: remove lvp_subpass::max_sample_count 
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
5e3d84e30a lavapipe: add attachment index to lvp_render_pass_attachment 
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
5cf568ce09 lavapipe: remove lvp_subpass_attachment::layout 
unused

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
eaa82252f9 lavapipe: remove lvp_subpass_attachment::in_render_loop 
this isn't used

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
afd8820d66 lavapipe: use framebuffer attachment_count member instead of renderpass 
according to spec, these must be equal

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
dd70ff3b8c lavapipe: remove some unused struct members 
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Mike Blumenkrantz
d103d5bb5d lavapipe: stop reading renderpass during pipeline creation 
this is unnecessary and is going to be annoying in the future

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13349>
 2021-10-19 01:18:24 +00:00
Dave Airlie
cae1ef0a11 clover: use max shader sampler view/images queries for clover. 
This is probably sane than my last answer to this question

Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13398>
 2021-10-19 01:03:58 +00:00
Mike Blumenkrantz
dfd0f5dbfd zink: move last of lazy descriptor state updating back to lazy-only code 
hybrid mode is controlled by the caching manager, so state tracking is irrelevant

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13350>
 2021-10-19 00:51:50 +00:00
Mike Blumenkrantz
140d3ea8c6 zink: add an early return for zink_descriptors_update_lazy_masked() 
no point in generating pools/sets that won't be used here

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13350>
 2021-10-19 00:51:50 +00:00
Mike Blumenkrantz
7c840f5103 zink: move push descriptor updating into lazy-only codepath 
this was a bit confusing to read, and I originally left it in the hybrid
path to enable fallbacks to push descriptors in hybrid mode. the problem with
that idea is that it's impossible: the constant buffer set is the one set
that will never, ever trigger a fallback, so leaving it there just leaves
room for error and confusion

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13350>
 2021-10-19 00:51:50 +00:00
Mike Blumenkrantz
b140d58b1f zink: don't update lazy descriptor states in hybrid mode 
I'm not 100% sure how, but this breaks tomb raider

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13350>
 2021-10-19 00:51:50 +00:00
Mike Blumenkrantz
75e51138b1 zink: assert compute descriptor key is valid before hashing it 
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13350>
 2021-10-19 00:51:50 +00:00
Mike Blumenkrantz
497ce3c38a zink: clear descriptor refs on buffer replacement 
the bo here can only ever be destroyed before it gets reused, so prune
it from the descriptor cache immediately

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13350>
 2021-10-19 00:51:50 +00:00
Mike Blumenkrantz
e66558985a zink: fully zero surface creation struct 
gotta get those holes for caching

cc: mesa-stable

Reviewed-by: Hoe Hao Cheng <haochengho12907@gmail.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13410>
 2021-10-19 00:33:50 +00:00
Mike Blumenkrantz
a2789fde0c zink: add a read barrier for indirect dispatch 
using the draw stage here doesn't make much sense, but that's what the
spec says, so let's git er done

fixes dEQP-GL45.functional.compute.indirect_dispatch* on radv

Cc: mesa-stable

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13381>
 2021-10-19 00:17:00 +00:00
Mike Blumenkrantz
11dd9e4ee4 zink: use static array for detecting VK_TIME_DOMAIN_DEVICE_EXT 
there's only a few possible values for this, so just use a static array
to avoid leaking

Fixes: 039078fe97 ("zink: slight refactor of load_device_extensions()")

Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13360>
 2021-10-19 00:02:39 +00:00
Neha Bhende
061610a7dd st: Fix comments in commit be6d584de4 
This patch is adding comments as suggested by Ilia in MR

Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13423>
 2021-10-18 21:30:03 +00:00
Karol Herbst
753f595e3d clover/api: fix clGetMemObjectInfo for images 
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13424>
 2021-10-19 06:55:38 +10:00
Karol Herbst
b4f9b15dd0 clover/formats: pass in cl_mem_flags for better format checking 
This allows us to advertise more formats depending on how the image is
getting used inside a kernel.

Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13424>
 2021-10-19 06:55:34 +10:00
Karol Herbst
f09e6c1c5f clover/format: Full rework on how we declare supported images. 
While at it also remove CL_LUMINANCE and CL_INTENSITY, which are optional
but also quite broken.

Also advertize all formats we can already support and make the list easier
to read. Also adds support for newer formats.

v2: fixup packing for non-8 bits (airlied)

Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13424>
 2021-10-19 06:55:22 +10:00
Neha Bhende
be6d584de4 st: Fix 64-bit vertex attrib index for TGSI path 
Patch 77c2b022a0 removed lowering of 64-bit vertex attribs to 32bits.
This has thrown TGSI translation off the guard for 64bit attrib.
This lead to fail/crash of 1000+ piglit tests.

This patch basically fixes 64 bit attrib index for TGSI shader by adding placeholder
for second part of a double attribute.
It fixes all regressed piglit tests.

A big help from Charmaine to fix this regression
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

Fixes: 77c2b022a0 ("st/mesa: remove lowering of 64-bit vertex attribs to 32 bits")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13363>
 2021-10-18 19:02:55 +00:00
Marek Olšák
e65d6f45d2 radeonsi: reorder and don't print patch level DRM version in the renderer string 
Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13392>
 2021-10-18 18:37:09 +00:00
Marek Olšák
f9d7db0262 ac,radeonsi: print a lowercase codename in the renderer string 
to make it stand out less

Reviewed-by: Zoltán Böszörményi <zboszor@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13392>
 2021-10-18 18:37:09 +00:00
Marek Olšák
cbcdcd42fc radeonsi: enable shader culling on Navi1x consumer SKUs as well 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13393>
 2021-10-18 18:08:59 +00:00
Marek Olšák
8cf802e8ef radeonsi: replace the GS prolog with a monolithic shader variant 
It only exists because of the hw bug and is used very rarely.
Let's simplify it.

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13393>
 2021-10-18 18:08:59 +00:00
Marek Olšák
62798d2c1f radeonsi: don't pass NULL into si_get_nir_shader 
so that we always have the shader key there

Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13393>
 2021-10-18 18:08:59 +00:00
Danylo Piliaiev
3350957f3c drirc: Apply vk_dont_care_as_load workaround to Forsaken Remastered 
Game has one renderpass which loads attachment with DONT_CARE, does
nothing, and writes it back.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/5437

Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Reviewed-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13367>
 2021-10-18 17:26:41 +00:00
Danylo Piliaiev
ebca227db1 turnip: implement vk_dont_care_as_load workaround 
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13367>
 2021-10-18 17:26:41 +00:00
Danylo Piliaiev
3d69800a0b driconf: add vk_dont_care_as_load workaround option 
It's easy to make a mistake of using VK_ATTACHMENT_LOAD_OP_DONT_CARE
when LOAD_OP_LOAD should be used since all desktop GPUs do the same
thing (nothing) for both of them.

However tiler GPUs do actually care about them.

Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Reviewed-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13367>
 2021-10-18 17:26:41 +00:00
Danylo Piliaiev
fd31989ecb turnip: add support for dirconf 
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13367>
 2021-10-18 17:26:41 +00:00
Samuel Pitoiset
5b797bd485 radv: fix OpImageQuerySamples with non-zero descriptor set 
The descriptor set was always 0 because it wasn't gathered by the
shader info pass.

This fixes CPU crashes with
arb_shader_texture_image_samples-builtin-image and Zink.

Cc: 21.3 mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13411>
 2021-10-18 16:47:50 +00:00
Connor Abbott
de568c3b2c tu/clear_blit: Stop creating a franken-image for staging blits 
Extricate the last use of tu_image_*.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:39 +00:00
Connor Abbott
9803c1aa10 tu: Remove cross-check scaffolding 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:39 +00:00
Connor Abbott
d785aea530 tu: Switch clear/blit to fdl6_view and cross-check 
This will help us create staging resources with a Y8 format and avoids
calling into the Vulkan-level entrypoints which will have to be changed
to use vk_image and vk_image_view.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:39 +00:00
Connor Abbott
1874e12f19 tu: Use fdl6_view in tu_image_view and cross-check 
Because some of the fields aren't filled out when a format doesn't
support rendering, we temporarily clear the structure so that we can
compare.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:39 +00:00
Connor Abbott
5509132a80 freedreno/fdl: Add fdl6_view 
This is mostly based on tu_image_view. The notable difference is that we
don't handle choosing the correct plane out of multiple planes when
indicated by the aspect, which means that there is no equivalent of
VK_IMAGE_ASPECT_PLANE_1 etc. This is expected to be done in the driver,
and note that freedreno gallium handles this very differently anyway.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:38 +00:00
Connor Abbott
464b9d6bf1 freedreno/fdl: Add mip_level to fdl_layout 
We need this when calculating the descriptors in the image view.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:38 +00:00
Connor Abbott
7bcccd1f08 freedreno/fdl: Constify fdl6_get_ubwc_blockwidth() 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:38 +00:00
Connor Abbott
7a90aa8d2e vk/format, v3dv: Add a vulkan -> pipe swizzle helper 
And use it to replace the one in v3dv.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13359>
 2021-10-18 16:00:38 +00:00
Pierre-Eric Pelloux-Prayer
7a2e40df5e Revert "gallium: add a is_dri_blit_image bool to pipe_blit_info" 
This reverts commit 22a1b7c5b3.

The only use was radeonsi and it switched to PIPE_BIND_DRI_PRIME
instead.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13362>
 2021-10-18 17:16:53 +02:00