fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-01-04 00:30:11 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
95460 commits 64 branches 915 tags 998 MiB
Commit graph

96 commits

Author SHA1 Message Date
Marek Olšák
61187c1689 gallium/u_threaded: rename IGNORE_VALID_RANGE -> NO_INFER_UNSYNCHRONIZED 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-08-28 21:45:33 +02:00
Marek Olšák
d308460586 gallium/radeon: reallocate suballocated buffers when exported 
This should fix exports of suballocated buffers.

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-07-17 10:50:39 -04:00
Marek Olšák
c784015643 gallium/radeon: allow suballocating textures 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-07-04 15:40:37 +02:00
Marek Olšák
d4fac1e1d7 gallium/radeon: enable suballocations for VRAM with no CPU access 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-07-04 15:40:37 +02:00
Marek Olšák
b09a22ad21 gallium/radeon: remove RADEON_FLAG_CPU_ACCESS 
https://lists.freedesktop.org/archives/amd-gfx/2017-June/010591.html

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-07-04 15:40:37 +02:00
Marek Olšák
fee2883bd7 gallium/radeon: ignore PIPE_BIND_SHARED for buffers 
BO exports can't be predicted this way.

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-07-04 15:40:37 +02:00
Samuel Pitoiset
e8df89d2c5 gallium/radeon: fix initialization of new resource bindless fields 
r600_resource objects are not calloc'd.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2017-06-15 11:56:21 +02:00
Marek Olšák
7166773f90 radeonsi: implement replace_buffer_storage for the threaded context 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
 2017-05-15 13:01:33 +02:00
Marek Olšák
b40d8026fa gallium/radeon: subclass threaded_transfer 
v2: use assert on rtransfer->b.staging

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
 2017-05-15 13:01:33 +02:00
Marek Olšák
b4fc399c08 gallium/radeon: subclass threaded_resource 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
 2017-05-15 13:01:33 +02:00
Marek Olšák
93d549b2af gallium/radeon: handle other map buffer flags from the threaded context 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
 2017-05-15 13:01:33 +02:00
Marek Olšák
e11f7e1d59 gallium/radeon: handle TC_TRANSFER_MAP_THREADED_UNSYNC 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
 2017-05-15 13:01:33 +02:00
Marek Olšák
42fe45b451 gallium/radeon: require both WRITE and FLUSH_EXPLICIT in buffer_flush_region 
spotted randomly.

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
 2017-05-15 13:01:33 +02:00
Nicolai Hähnle
39f51b5db9 radeonsi: add missing initialization for userptr buffers 
Fix the accounting for memory usage of userptr buffers, which has been wrong
forever (or at least for a long time).

Also initialize flags. Without this initialization, the sparse buffer flag
might end up being set, which leads to staging buffers being used unnecessarily
(and incorrectly) in transfers to or from userptr buffers.

This works around VM faults that occur with the radeon kernel module when
running piglit ./bin/amd_pinned_memory decrement-offset map-buffer -auto

Fixes: e077c5fe65 ("gallium/radeon: transfers and invalidation for sparse buffers")
Reported-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2017-04-14 23:23:04 +02:00
Nicolai Hähnle
b52721e3b6 gallium/radeon: never use staging buffers with AMD_pinned_memory 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
 2017-04-13 17:36:26 +02:00
Nicolai Hähnle
e077c5fe65 gallium/radeon: transfers and invalidation for sparse buffers 
Sparse buffers can never be mapped by the CPU.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2017-04-05 10:37:19 +02:00
Nicolai Hähnle
5969a373a1 gallium/radeon: implement sparse buffer creation 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2017-04-05 10:37:19 +02:00
Marek Olšák
04e6977e5d gallium/radeon: reference pipe_resource in pipe_transfer 
for threaded gallium

Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
 2017-03-17 18:30:21 +01:00
Marek Olšák
a41587433c gallium/radeon: add R600_RESOURCE_FLAG_UNMAPPABLE 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-02-18 01:22:08 +01:00
Marek Olšák
9434421213 gallium/radeon: change r600_aligned_buffer_create to take flags, not bind 
All call sites set bind = 0. The next commit will use this.

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-02-18 01:22:08 +01:00
Marek Olšák
a550fbb510 gallium/radeon: use TCC line size as alignment in other places 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-02-18 01:22:08 +01:00
Marek Olšák
2ca3548eb9 gallium/radeon: remove the internal u_upload_mgr pointer 
also remove the BIND flags

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Tested-by: Edmondo Tommasina <edmondo.tommasina@gmail.com>
Tested-by: Charmaine Lee <charmainel@vmware.com>
 2017-02-14 21:46:16 +01:00
Marek Olšák
dc7483f445 gallium/radeon: ignore the level parameter in buffer_transfer_map 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-02-10 11:27:50 +01:00
Marek Olšák
d86099df0a gallium/radeon: fix performance of buffer readbacks 
We want cached GTT for all non-persistent read mappings.
Set level = 0 on purpose.

Use dma_copy, because resource_copy_region causes a failure in the PBO
read of piglit/getteximage-luminance.

If Rocket League used the READ flag, it should get cached GTT.

v2: mask out UNSYNCHRONIZED

Cc: 13.0 17.0 <mesa-stable@lists.freedesktop.org>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-02-10 11:27:50 +01:00
Marek Olšák
cecc068774 gallium/radeon: allow VRAM-only placements again on APUs & recent amdgpu 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2017-01-30 13:27:14 +01:00
Marek Olšák
bf4d102ea3 gallium/radeon: add radeon_surf::is_linear 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-11-01 22:33:13 +01:00
Nicolai Hähnle
e56e1f8119 gallium/radeon: use the new parent/child pools for transfers 
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97894
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2016-10-05 15:42:07 +02:00
Marek Olšák
e43bd861e8 radeonsi: track buffer bind history 
similar to gl_buffer_object::UsageHistory

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
 2016-10-04 16:11:58 +02:00
Nicolai Hähnle
13cb41f666 radeon/video: don't use sub-allocated buffers 
Cc: Christian König <christian.koenig@amd.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97976
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97969
Reviewed-by: Christian König <christian.koenig@amd.com>
 2016-09-30 12:38:29 +02:00
Michel Dänzer
8d8c440ebf gallium/radeon: Initialize pipe_resource::next to NULL 
Fixes lots of piglit tests crashing due to using uninitialized memory.

Fixes: ecd6fce261 ("mesa/st: support lowering multi-planar YUV")
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2016-09-28 10:39:22 +09:00
Marek Olšák
5981ab5445 gallium: remove PIPE_BIND_TRANSFER_READ/WRITE 
not used in any useful way

Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
 2016-09-08 22:51:33 +02:00
Marek Olšák
e7a73b75a0 gallium: switch drivers to the slab allocator in src/util 2016-09-06 14:24:04 +02:00
Marek Olšák
0d2e43fcb1 gallium/radeon: derive buffer placement and flags only at initialization 
Invalidated buffers don't have to go through it.

Split r600_init_resource into r600_init_resource_fields and
r600_alloc_resource.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-09-05 18:01:15 +02:00
Marek Olšák
f4b977bf3d gallium/radeon: add r600_resource::vram_usage and gart_usage 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-08-06 13:56:14 +02:00
Marek Olšák
700de07771 radeonsi: implement buffer_subdata without indirect calls 
There is less noise in CPU profile data now.

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-07-23 13:33:42 +02:00
Marek Olšák
1ffe77e7bb gallium: split transfer_inline_write into buffer and texture callbacks 
to reduce the call indirections with u_resource_vtbl.

The worst call tree you could get was:
  - u_transfer_inline_write_vtbl
    - u_default_transfer_inline_write
      - u_transfer_map_vtbl
        - driver_transfer_map
      - u_transfer_unmap_vtbl
        - driver_transfer_unmap

That's 6 indirect calls. Some drivers only had 5. The goal is to have
1 indirect call for drivers that care. The resource type can be determined
statically at most call sites.

The new interface is:
  pipe_context::buffer_subdata(ctx, resource, usage, offset, size, data)
  pipe_context::texture_subdata(ctx, resource, level, usage, box, data,
                                stride, layer_stride)

v2: fix whitespace, correct ilo's behavior

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Acked-by: Roland Scheidegger <sroland@vmware.com>
 2016-07-23 13:33:42 +02:00
Marek Olšák
7db10093d3 gallium/radeon: boolean -> bool, TRUE -> true, FALSE -> false 
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Vedran Miletić <vedran@miletic.net>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-06-25 23:13:42 +02:00
Marek Olšák
d5383a7d31 gallium/radeon: use r600_resource_reference 
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Vedran Miletić <vedran@miletic.net>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-06-25 23:13:42 +02:00
Marek Olšák
d5491a81ff gallium/radeon: don't use the DMA ring for pipelined buffer uploads 
Submitting a DMA IB flushes the GFX IB and all GPU caches.

Vedran Miletić said:
  "On Tonga 380X, this improves The Talos Principle from 8.3 fps to 28.3 fps
   (all graphics settings Ultra, 4xAA, 1080p resolution with downsampling
   from 1200p)."

Some anonymous dude said:
   R9 390 results:
      Tomb Raider (normal settings): 80 -> 88 FPS
      Talos Principle (custom settings): 23 -> 56 FPS
      Metro Last Light Redux (default benchmark settings): 39 -> 40 FPS

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Vedran Miletić <vedran@miletic.net>
Tested-by: Grazvydas Ignotas <notasas@gmail.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
 2016-06-04 15:42:33 +02:00
Marek Olšák
f330b7a14f gallium/radeon: handle VRAM_GTT placements as having slow CPU reads 
not sure if we should include GTT WC too

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-05-19 12:35:50 +02:00
Nicolai Hähnle
0558564200 gallium/radeon: add radeon_emitted to check for non-trivial IBs 
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2016-05-17 15:28:39 -05:00
Nicolai Hähnle
562c4a17b7 winsys/radeon: remove use_reusable_pool parameter from buffer_create 
All callers set this parameter to true.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2016-04-27 11:16:41 -05:00
Nicolai Hähnle
13acf2b243 gallium/radeon: remove use_reusable_pool parameter from r600_init_resource 
All callers set it to true.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2016-04-27 11:16:41 -05:00
Nicolai Hähnle
a17911ceb1 gallium/radeon: handle failure when mapping staging buffer 
Cc: "11.1 11.2" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
 2016-04-14 16:29:23 -05:00
Marek Olšák
5b6a0b7fc0 gallium/radeon: set GTT WC on tiled textures 
Just for consistency. This should have no effect, because OpenGL textures
always go to VRAM.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
 2016-04-12 14:29:48 +02:00
Marek Olšák
5a4b74d1ba gallium/radeon: relax requirements on VRAM placements on APUs 
This makes Tonga with vramlimit=128 2x faster in Heaven.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
 2016-04-12 14:29:48 +02:00
Marek Olšák
1dd8832e04 gallium/radeon: allow allocating textures >= 4 GB 
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-04-12 14:29:48 +02:00
Marek Olšák
7e78b5ed38 pb_buffer: switch pb_buffer::size to 64 bits 
being able to allocate more than 4 GB may be useful

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-04-12 14:29:47 +02:00
Marek Olšák
6b187bbd9f gallium/radeon: disallow reallocation of shared buffers 
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-03-09 15:02:26 +01:00
Marek Olšák
ecbd3aba17 gallium/radeon: if we can't discard a whole resource, discard the range instead 
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
 2016-03-09 15:02:26 +01:00