fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-23 22:00:13 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
184006 commits 64 branches 914 tags 1 GiB
Commit graph

490 commits

Author SHA1 Message Date
Mike Blumenkrantz
7a169254c5 zink: add COHERENT requirement for CACHED memory 
zink doesn't handle non-coherent cached memory correctly, so ensure
that scenario is never hit

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23728>
 2023-06-20 16:53:31 +00:00
Mike Blumenkrantz
ff1e667e45 zink: strip format list when disabling mutable during image creation 
drivers shouldn't be getting a format list if it won't be used

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23514>
 2023-06-15 05:02:37 +00:00
Mike Blumenkrantz
9e83723a21 zink: add srgb mutable for all resources by default 
this should enable compression on more intermediate fb attachments

it also means that VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT can now be set
on images where ZINK_BIND_MUTABLE is not set, so non-resource APIs need
to check ZINK_BIND_MUTABLE

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23514>
 2023-06-15 05:02:37 +00:00
Mike Blumenkrantz
4edbe8f5a0 zink: add mem debugging 
modeled off turnip's debug infra, this adds debug printing for oom
scenarios

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23653>
 2023-06-15 01:31:24 +00:00
Mike Blumenkrantz
4e87d81d20 zink: add a dgc debug mode for testing 
this is useful for drivers trying to implement DGC since there is no cts

do not use.

it will not make anything faster.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23550>
 2023-06-14 12:37:24 +00:00
Mike Blumenkrantz
8f56228ace zink: only try to create srgb mutable images if the vk format is supported 
otherwise this is just a regular single-format image

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23626>
 2023-06-13 17:45:38 +00:00
Mike Blumenkrantz
81834a211d zink: check for cached mem correctly when mapping buffer 
bo placement is the mem index, not the mem flags

Fixes: 52f27cda05 ("zink: allow direct memory mapping for any COHERENT+CACHED buffer")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23511>
 2023-06-08 14:30:39 +00:00
Julia Tatz
81b0840caa zink: Implement PIPE_CAP_RESOURCE_FROM_USER_MEMORY 
Needed for GL_AMD_pinned_memory & zero-copy support in opencl

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23199>
 2023-05-25 02:41:23 +00:00
Mike Blumenkrantz
8d58fa5787 zink: only add feedback loop usage bit if extension is supported 
cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22960>
 2023-05-15 22:52:57 +00:00
Mike Blumenkrantz
443e098f7a zink: make mesa_logw separate from perf_debug 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22899>
 2023-05-09 22:16:22 +00:00
Mike Blumenkrantz
24350064ca zink: fix uncached memory readback 
the inner conditional here didn't include uncached readback, meaning
that many (most?) buffers allocated with uncached memory (i.e., BAR) were
being read back directly instead of using staging resources to be faster

at some point this inner conditional should be reevaluated to determine
whether it still does anything, but this is not that time

fixes, among other things, loading in DOOM2016 on some GPUs

Fixes: 52f27cda05 ("zink: allow direct memory mapping for any COHERENT+CACHED buffer")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22907>
 2023-05-09 00:56:19 +00:00
Mike Blumenkrantz
8e75378a2d zink: delete persistent map tracking 
this was never needed and never did anything: zink only uses COHERENT
memory, which is always available on queue submission, so it was all
just pointless code

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22907>
 2023-05-09 00:56:19 +00:00
Mike Blumenkrantz
3909471288 zink: use a perf_debug() macro for debug message logging of copy box warning 
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22196>
 2023-04-20 02:52:16 +00:00
Mike Blumenkrantz
366b79fa10 zink: only print copy box warning once per resource 
this otherwise gets spammy

cc: mesa-stable

Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22196>
 2023-04-20 02:52:16 +00:00
Mike Blumenkrantz
31a0de9921 zink: make general bo allocation more robust by iterating 
previously there was a fallback path here (broken by f6d3a5755f)
which would attempt to demote BAR allocations to other heaps on failure
to avoid oom

this was great, but it's not the most robust solution, which is to iterate
all the memory types matching the given heap and try them in addition to having
a demotion fallback

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22479>
 2023-04-16 23:55:30 +00:00
Mike Blumenkrantz
9d923b14f9 zink: restore BAR allocation failure demotion 
this restores the fallback used when BAR allocation fails due to oom
by re-selecting memoryTypeIndex after the heap demotion

Fixes: f6d3a5755f ("zink: zink_heap isn't 1-to-1 with memoryTypeIndex")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22479>
 2023-04-16 23:55:30 +00:00
Mike Blumenkrantz
561b64cf55 zink: slightly rework memoryTypeIndex selection to pre-determine heap 
should be no functional changes

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22479>
 2023-04-16 23:55:30 +00:00
Mike Blumenkrantz
085c9efbf3 zink: move memoryTypeIndex selection down in general bo allocation 
no functional changes

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22479>
 2023-04-16 23:55:30 +00:00
xurui
f66e6b671c zink: Some return values of malloc should be checked 
Signed-off-by: xurui <xurui@kylinos.cn>
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22328>
 2023-04-13 13:40:22 +00:00
Mike Blumenkrantz
7704773619 zink: handle swapchain handoffs around makecurrent 
when a new resource is created for an extant swapchain, the existing
acquire (if any) should be transferred to the resource to ensure
expected behavior

this should be enough to fix piglit's glx-make-current

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22431>
 2023-04-12 21:43:35 +00:00
Mike Blumenkrantz
ca43ecefa4 zink: handle swapchain creation failure less lazily 
this is a real scenario

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22027>
 2023-03-21 01:39:39 +00:00
Mike Blumenkrantz
d862d708e2 zink: use res->queue to auto-handle queue transitions back to gfx queue 
much simpler

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21733>
 2023-03-17 07:25:04 +00:00
Mike Blumenkrantz
d7b04c110b zink: remove redundant dmabuf_acquire setting 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21733>
 2023-03-17 07:25:04 +00:00
Mike Blumenkrantz
2fd2133c9d zink: track current queue for resources 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21733>
 2023-03-17 07:25:04 +00:00
Mike Blumenkrantz
81a4163375 zink: fix copy box merging adjacency 
these cases need to increase the box size, not just adjust the offset

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21921>
 2023-03-15 16:42:19 +00:00
Mike Blumenkrantz
32f74c4db5 zink: fix copy box iteration when adding 
need to use the iterator, not the base pointer

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21921>
 2023-03-15 16:42:19 +00:00
Mike Blumenkrantz
2409ddb5db zink: fix copy box iteration 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21907>
 2023-03-14 21:25:55 +00:00
Mike Blumenkrantz
fe6f0692ed zink: rework zink_resource::valid_buffer_range 
this is now the valid buffer region for the "main" command buffer,
and all transfer ops store their regions in the copy boxes

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21802>
 2023-03-14 16:23:06 +00:00
Mike Blumenkrantz
46f98da188 zink: add a mechanism to trigger copy box resets from batch state reset 
the resource isn't available during batch state reset, so a new flag
is needed to force a reset the next time the copy boxes would be used

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21779>
 2023-03-08 03:50:33 +00:00
Mike Blumenkrantz
aaca91eb79 zink: add a mechanism for managing TRANSFER_DST buffer barriers 
this enables successive or unrelated transfer writes to avoid triggering
barriers, and ensuing reads of those writes should trigger their own
barriers

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21779>
 2023-03-08 03:50:33 +00:00
Mike Blumenkrantz
54f3c589d5 zink: track the last write access for resources 
this enables some optimization

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21779>
 2023-03-08 03:50:33 +00:00
Mike Blumenkrantz
1aa62912b7 zink: don't unset existing access when adding resource binds 
this breaks barrier calcs, but it was fine since there was a pre-barrier

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21739>
 2023-03-07 01:57:41 +00:00
Mike Blumenkrantz
a0f3d171f6 zink: eliminate pre barrier for adding resource binds 
this will automatically be handled by the copies below

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21739>
 2023-03-07 01:57:41 +00:00
Mike Blumenkrantz
0d8a54f913 zink: avoid ballooning of copy box tracking 
* if the proposed box is smaller than an existing box then don't add it,
* if the proposed box is adjacent to an existing box, expand
* if the proposed box is larger than an existing box, replace

this reduces the chances of having a ton of copy boxes to iterate over

also add a perf warning in case a ton of copy boxes exist

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21665>
 2023-03-06 03:47:06 +00:00
Mike Blumenkrantz
52f27cda05 zink: allow direct memory mapping for any COHERENT+CACHED buffer 
some drivers may provide this in heaps that get used by non-staging resources,
so avoid extra copies in that case

unlike the previous attempt at this optimization, this utilizes the screen-based
context for thread-safe transfers, which should avoid races/crashes

fix #8171

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21452>
 2023-02-27 03:50:14 +00:00
Mike Blumenkrantz
d78de2a962 zink: add locking for zink_screen::copy_context and defer creation 
the copy context isn't always used, so this allows its creation to
be deferred and potentially save a bunch of memory

also add locking for multi-context thread safety

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21452>
 2023-02-27 03:50:14 +00:00
Mike Blumenkrantz
fa6e6545b1 zink: add some tracking for copy box regions 
this enables tracking per-miplevel pipe_boxes for copy operations that
can then be used to avoid emitting barriers for successive copy operations
without overlapping regions

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21397>
 2023-02-24 05:27:31 +00:00
Erik Faye-Lund
176add76ad zink: get rid of needless dependency 
We haven't needed this header since 7f56fd9655 ("zink: it's kopperin'
time"), so let's get rid of it and the dependency that comes with it.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21441>
 2023-02-22 12:23:39 +00:00
SoroushIMG
96849363eb zink: free resource objects' views array during destruction 
since the array is not ralloc managed, it has be explicitly freed.

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21285>
 2023-02-13 19:00:06 +00:00
Mike Blumenkrantz
4cda98c827 zink: implement a scaling descriptor buffer size 
previously descriptor buffers were sized to allow for 25,000 descriptors

this is a great number.

but in some scenarios it's overkill, and it's theoretically possible that
it might be underkill in others (citation needed), so add some handling
for both cases to save small amounts of vram on average and not crash
in the distant future when hypercomputers try running drawoverhead

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21246>
 2023-02-13 10:27:16 +00:00
Mike Blumenkrantz
cd446b87e1 zink: add newlines to some debug printfs 
cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21239>
 2023-02-10 19:42:53 +00:00
Mike Blumenkrantz
dc91f2c71b zink: set PIPE_CAP_SURFACE_REINTERPRET_BLOCKS 
this fixes perf for CompressedTexSubImage and makes DOOM2016 run at full speed

ref #8223

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21218>
 2023-02-09 09:54:27 -05:00
Mike Blumenkrantz
36595e94c7 zink: avoid the descriptor set multiplier for bindless buffers 
the bindless descriptor buffer is already correctly sized, so it needs
to avoid the huge set multiplier or it'll explode all available vram

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21216>
 2023-02-09 08:08:22 -05:00
Mike Blumenkrantz
03c2bdda60 zink: use VK_EXT_multisampled_render_to_single_sampled for EXT_multisample_render_to_texture 
this extension was added for the purpose of emulating the GL ext,
and using it is reasonably straightforward

the only (somewhat) invasive part is modifying the renderpass/dynamic hashes
to have samplecounts in the key, but this is also not too much work

now only fbfetch requires real renderpasses, and everything else is dynamic

fixes #7559

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20883>
 2023-02-01 10:08:57 +00:00
Mike Blumenkrantz
d745e3b0ab zink: always unref old images when adding new binds 
at some point this was correct, but refactoring has since occurred,
and this ends up leaking storage image objects

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20867>
 2023-01-31 16:31:46 +00:00
Mike Blumenkrantz
01d2e7afce zink: don't add dmabuf export type if dmabuf isn't supported 
avoid trying to create dmabuf-exportable resources too

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20791>
 2023-01-31 15:57:13 +00:00
Mike Blumenkrantz
3c562cfc06 zink: set vkusage/vkflags for buffer resource objects 
this needs to be populated for other places in the driver that need it

cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20912>
 2023-01-27 19:23:29 +00:00
Mike Blumenkrantz
c545300f30 zink: add VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT for buffers if ext is enabled 
cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20912>
 2023-01-27 19:23:29 +00:00
Mike Blumenkrantz
07809c4527 Revert "zink: allow direct memory mapping for any COHERENT+CACHED buffer" 
This reverts commit a3552048c7.

on some drivers this catches qbos, which then hits the below assert.
needs more investigation

Fixes: a3552048c7 ("zink: allow direct memory mapping for any COHERENT+CACHED buffer")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20912>
 2023-01-27 19:23:28 +00:00
Mike Blumenkrantz
87a9018ff9 zink: reorder commands more aggressively 
by starting resources in the unordered state in a given batch, they
gain more opportunities to be promoted to the barrier cmdbuf and avoid
breaking renderpasses

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20890>
 2023-01-27 02:42:56 +00:00