summaryrefslogtreecommitdiff
path: root/lib/rendercopy_gen9.c
AgeCommit message (Collapse)Author
2019-04-29lib/rendercopy: Configure MOCS more consistentlyVille Syrjälä
Unify the MOCS to be more consistently across the platforms. Currently gen8+ are specifyig UC whereas earlier platforms generally use PTE. Let's make everyone more or less specify L3+PTE. Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2019-04-29lib/rendercopy: Add fp16 support for gen4+Ville Syrjälä
Allow copying between fp16 surfaces. We'll use the FLOAT surface format since that's all the display supports currently. Hopefully the hardware gives us a 1:1 copy, at least if the input doesn't contain crazy infs/nans etc. We could choose UNORM instead but that won't work for eventually exposing fp16+ccs. Although we do need to replace the simple bpp value with a more specific format type to get 10bpc+ccs working as well. Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2019-04-04lib/rendercopy: Assert that buffer dimensions/stride are acceptableVille Syrjälä
Sprinkle some asserts into rendercopy to make sure we don't try to exceed the render engine surface size/stride limitations. Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2019-03-11lib/rendercopy: Add support for Yf/Ys tiling to gen9 rendercopyVille Syrjälä
Set up the surface state accordingly to support Yf/Ys tiling. >From DK: Rebase. Move support to gen-9 surface state Cc: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Cc: Katarzyna Dec <katarzyna.dec@intel.com> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2019-03-11lib/rendercopy: Copy gen8 surface state definition to gen-9 headerDhinakaran Pandiyan
Create a gen9 specific struct so that the gen-9+ Yf/Ys tiling bits can be added there. Suggested-by: Katarzyna Dec <katarzyna.dec@intel.com> Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2018-11-20lib/rendercopy: Implement support for 8/16 bppMaarten Lankhorst
To handle drawing 16 bpp formats correctly with odd x/w, we need to use the correct bpp to rendercopy. Now that everything sets bpp in igt_buf, fix the rendercopy support to use it and set the correct format. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> [mlankhorst: Add assert(src->bpp == dst->bpp)]
2018-10-15libs: Add rendercopy support for GEN11Kalamarz, Lukasz
This patch introduces a render copy shader for GEN11. The plumbing is same as with GEN9, so we can reuse it, extracting the common parts, and wrapping it in GEN-specific helpers. v2: Added gen11 shader source path next to its binary form Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Antonio Argenziano <antonio.argenziano@intel.com> Cc: Lucas De Marchi <lucas.demarchi@intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Katarzyna Dec <katarzyna.dec@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2018-10-04lib/i915: Move shaders directoryKatarzyna Dec
In shaders/ directory we got Intel specific information. As igt is a project for more vendors, let's move this directory to lib/i915. v2: Changed shaders directory path in library files comments. Signed-off-by: Katarzyna Dec <katarzyna.dec@intel.com> Cc: Arkadiusz Hiler <arkadiusz.hiler@intel.com> Cc: Petri Latvala <petri.latvala@intel.com> Cc: Kalamarz Lukasz <lukasz.kalamarz@intel.com> Cc: Antonio Argenziano <antonio.argenziano@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2018-07-18lib/rendercopy: Use gen4 definitions if applicableLukasz Kalamarz
Instead of using definitions duplicated in gen7_render header, we should use the oldest definition that is working with chosen gen. This patch reuse gen6 definitons if registers/fields/shifts that were introduced in other genX_render headers. v3: Rebase and checkpatch Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Cc: Katarzyna Dec <katarzyna.dec@intel.com> Cc: Antonio Argenziano <antonio.argenziano@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2018-07-06lib/rendercopy: Add enough surface state for AUX_CCS_EVille Syrjälä
Populate the gen8+ SURFACE_STATE aux bits correctly. Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2018-07-06lib/rendercopy: Set the upper 32bits of surface base address on gen8+Ville Syrjälä
gen8 introduces 48 bit virtual addresses. Set both dwords correctly as otherwise the presumed_offset will not match what we actually have stored in the surface state if the buffer is located somewhere above 4GiB. I guess we're not currently using 48bit addresses with rendercopy? Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2018-07-05lib: Constify igt_bufVille Syrjälä
No one generally needs to modify the igt_bufs we pass around, so make them const. Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2018-07-03lib/rendercopy: Simplify reloc offsetsVille Syrjälä
Remove the hardcoded dword offsets for the relocs and instead rely fully on intel_batchbuffer_subdata_offset(). Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
2018-07-03lib/rendercopy: Use gen8_wm_kernel__affineChris Wilson
The shaders/blit.g7a has weird artefacts (random pixel kill) when drawing to an odd destination coordinate. Rather than debug the issue with the asm/assembler, replace the kernel with the one used by SNA for simple copies. Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com> #chv, skl Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
2018-06-14lib/gen9_render: Header cleanupLukasz Kalamarz
This patch cleans gen9 header from a duplicate definition and it dependency. Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Cc: Katarzyna Dec <katarzyna.dec@intel.com> Cc: Antonio Argenziano <antonio.argenziano@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Ewelina Musial <ewelina.musial@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2018-06-14lib/gen8_render: Cleanup of libsLukasz Kalamarz
This patch implements some changes in gen8_render header and all files that include it. Renamed all definition that were introduced in that file with prefix GEN8_* instead of previous GEN's one if they were not implemented there, otherwise dropped duplicates. Modified include to use gen7_render header instead of gen6. v2: Fixed commit message v3: fixed typo in commit msg Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Cc: Katarzyna Dec <katarzyna.dec@intel.com> Cc: Antonio Argenziano <antonio.argenziano@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Ewelina Musial <ewelina.musial@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2018-06-14lib/rendercopy: Use gen6 definitions if applicableLukasz Kalamarz
Instead of using definitions duplicated in gen7_render header, we should use the oldest definition that is working with chosen gen. This patch reuses gen6 definitons if registers/fields/shifts that were reintroduced in other genX_render headers. v2: Fixed commit message v3: fixed typos in commit msg Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Cc: Katarzyna Dec <katarzyna.dec@intel.com> Cc: Antonio Argenziano <antonio.argenziano@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Ewelina Musial <ewelina.musial@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2018-06-05lib: Rename all surfaceformat calls in libsLukasz Kalamarz
This patch is renaming all surfaceformat registers to use names introduced in surfaceformat.h instead of using per gen definitions v2: Drop GEN_ from register names. Applied that to other libs. Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com> Cc: Radoslaw Szwichtenberg <radoslaw.szwichtenberg@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
2018-04-24lib/intel_batchbuffer: Move batch functions from media/render/gpgpu libsKalamarz, Lukasz
Batch functions were copy/pasted across several libs. With moving it into intel_batchbuffer lib test can now be easly maintained without worrying that we forgot to modify older version of lib. v2: Added documentation into lib and rebased patch v3: Fixed typos and rebased patch v4: Fixed documentation issues v5: Rename, clean up of leftovers from previous version and documentation polishing v6: Fixing assert Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz@intel.com> Cc: Katarzyna Dec <katarzyna.dec@intel.com> Cc: Radoslaw Szwichtenberg <radoslaw.szwichtenberg@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Katarzyna Dec <katarzyna.dec@intel.com>
2017-12-07lib: copy intel_aub.h from libdrmScott D Phillips
No functionality related to aub is provided by libdrm aside from intel_aub.h which somewhat defines the file format. Move the header into this project to ease aub-related development. Signed-off-by: Scott D Phillips <scott.d.phillips@intel.com> Acked-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2016-11-09Revert "lib: use the local intel_aub.h file"Tomeu Vizoso
Emil prefers if the approach in v2 is used (it was sent around the time v1 had been applied). This reverts commit 438c8d7c688780337d271016d84a69aab0474097.
2016-10-27lib: use the local intel_aub.h fileEmil Velikov
File is provided by the libdrm_intel package which is optional. Since we already have a local copy of the file, we might as well use it ;-) Cc: Brian Starkey <brian.starkey@arm.com> Reported-by: Brian Starkey <brian.starkey@arm.com> Signed-off-by: Emil Velikov <emil.l.velikov@gmail.com> Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-08-13lib/rendercopy_gen9: Setup Push constant pointer before sending BTP commandsArun Siluvery
From Gen9, by default push constant command is not committed to the shader unit untill the corresponding shader's BTP_* command is parsed. This is the behaviour when set shader is enabled. This patch updates the batch to follow this requirement otherwise it results in gpu hang. Set shader need to be disabled if legacy behaviour is required. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=89959 Cc: Ben Widawsky <benjamin.widawsky@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Arun Siluvery <arun.siluvery@linux.intel.com> Tested-by: Mika Kuoppala <mika.kuoppala@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
2015-08-13lib/rendercopy_gen9: WaBindlessSurfaceStateModifyEnableMika Kuoppala
Don't set the size of bindless surface state on rendercopy. And as of doing so, take into account the workaround for setting the command size. This was tried during hunting for https://bugs.freedesktop.org/show_bug.cgi?id=89959. But no impact was found. Cc: Arun Siluvery <arun.siluvery@linux.intel.com> Reviewed-by: Arun Siluvery <arun.siluvery@linux.intel.com> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
2015-03-26igt.cocci: check the return values of various functionsThomas Wood
Add rules to fix unused-result warnings when compiling with _FORTIFY_SOURCE defined and apply them to the library and tests. Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Thomas Wood <thomas.wood@intel.com>
2015-02-02rendercopy/gen9: fix gem_render_copy 3d state setupImre Deak
Without emitting the default 3DSTATE_WM_DEPTH_STENCIL state the test will fail. Signed-off-by: Imre Deak <imre.deak@intel.com>
2014-11-06Rendercopy/skl: Remove redundant field to fix GPU hangZhao Yakui
After applying the commit(982f7eb238a0898c456e0574dee7c4507738d75f), the OUT_RELOC is updated on Broadwell and later, which is to handle the 64-bit field of gfx address internally. In such case some commands should be fixed, otherwise GPU hang will be triggered when running rendercopy. (It is already fixed on Broadwell) Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-10-17lib: various documentation fixesThomas Wood
Signed-off-by: Thomas Wood <thomas.wood@intel.com>
2014-09-30rendercopy/skl: Set the URB VS start address to 4Xiang, Haihao
A value less than 4 might result in GPU hang on simulation Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@linux.intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-09-30rendercopy/skl: Follow the spec to add the Pipeline selection maskZhao Yakui
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-09-30rendercopy/skl: Emit 3DSTATE_WM_HZ_OPZhao Yakui
This is from that on BDW. Without it, the pixel pipeline can't work well. Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-09-30rendercopy/skl: Fix the 3DSTATE_DS instruction lengthZhao Yakui
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-09-30rendercopy/skl: Fix the STATE_BASE_ADDRESS instruction lengthZhao Yakui
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-09-30rendercopy/skl: Set Instruction Buffer size Modify Enable to 1Zhao Yakui
This is ported from that on BDW. Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-09-30rendercopy/skl: update instruction lengthZhao Yakui
This is ported from that on BDW. v2: Only bump the prefix when we need to program the instruction differently with the previous generations. Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com> Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
2014-09-30rendercopy/skl: Pass the context to rendercopy function on SKLZhao Yakui
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Zhao Yakui <yakui.zhao@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
2014-09-30rendercopy/skl: Update 3DSTATE_SBEDamien Lespiau
SBE has now to be explicitely told which channels of which components are used by the pixel shader. Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
2014-09-30rendercopy/skl: Set the 3DSTATE_VF stateDamien Lespiau
This is to ensure the "Component Packing Enable" bit is set to 0. Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
2014-09-30rendercopy/skl: Start the gen9 rendercopy from the gen8 versionDamien Lespiau
v2 (Ben): Rebased on: commit ea11d103e0617e33bce6f11328521d15b13422b0 Author: Oscar Mateo <oscar.mateo@intel.com> Date: Tue Nov 12 11:50:35 2013 +0000 build: list all test/tool/lib source files in their own Makefile.sources v3: (Ben): Rebased on the doc/API rework. Probably needs review Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-10 06:10:49 +0000