We don't want depth/stencil fast clears or HiZ resolves; we want normal
drawing. Without this, the pixel pipeline doesn't work.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Damien Lespiau <damien.lespiau@intel.com>
Provide two arguments version, and verbose, which allow printing from an
arbitrary igt test. It will show system information (from build time,
not runtime), as well as the git SHA being used.
This will help reduce errors when people try to reproduce problems.
As an example if I want to verify someone is running the correct version
of a test, I could ask them to do:
bwidawsk@ironside ~/intel-gfx/intel-gpu-tools (master)$ sudo ./tests/gem_exec_nop --verbose
gem_exec_nop-git-3c5423b (Linux ironside 3.12.0-1-ARCH #1 SMP PREEMPT
Wed Nov 6 09:06:27 CET 2013 x86_64 GNU/Linux)
Time to exec x 1: 35.000µs (ring=render)
Time to exec x 2: 28.000µs (ring=render)
Time to exec x 4: 20.000µs (ring=render)
Time to exec x 8: 14.625µs (ring=render)
Time to exec x 16: 11.188µs (ring=render)
Time to exec x 32: 11.125µs (ring=render)
Time to exec x 64: 10.328µs (ring=render)
Time to exec x 128: 10.172µs (ring=render)
Time to exec x 256: 10.234µs (ring=render)
Time to exec x 512: 10.232µs (ring=render)
Time to exec x 1024: 10.121µs (ring=render)
Time to exec x 2048: 10.151µs (ring=render)
Time to exec x 4096: 11.474µs (ring=render)
Time to exec x 8192: 9.432µs (ring=render)
Time to exec x 16384: 6.003µs (ring=render)
Time to exec x 32768: 5.029µs (ring=render)
Time to exec x 65536: 4.206µs (ring=render)
Time to exec x 131072: 3.630µs (ring=render)
Subtest render: SUCCESS
--verbose is provided for completeness, but doesn't seem too useful at
the moement.
bwidawsk@ironside ~/intel-gfx/intel-gpu-tools (master)$ sudo ./tests/gem_exec_nop --version
gem_exec_nop-git-3c5423b (Linux ironside 3.12.0-1-ARCH #1 SMP PREEMPT
Wed Nov 6 09:06:27 CET 2013 x86_64 GNU/Linux)
I've put version.h in the root directory so that any subdir can access
it. I've added the tests usage since it's immediately useful, and done
easily via Daniels igt infrastructure work.
v2:
- Always print the version number.
- We want to print uname at runtime.
- Also prefix the i-g-t release version.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I did the same change in the Kernel a few months ago. This should help
not getting confused about which bit does what.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
It's what callers expect - pipe_crc_new is the function where
we pass a potential failure back to callers.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
No need to duplicate this all over the place.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Otherwise it may result in GPU hang
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Otherwise the stale data in the buffer
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
v2: Fixed the source register used for the send with EOT
Fixed the posted destination operand for the send with EOT
Reviewed-by: Zhao Yakui <yakui.zhao@intel.com>
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
v2: Fixed the source register used for the send with EOT
Fixed the posted destination operand for the send with EOT
v3: Workaround: Insert MEDIA_STATE_FLUSH after MEDIA_OBJECT.
Fixed the cache agent used in media_block_write message
Set Instruction Buffer size Modify Enable to 1, otherwise it may result in GPU hang
Reviewed-by: Zhao Yakui <yakui.zhao@intel.com>
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
It is to check whether media pipeline on render ring works. Codes
are copied and modified from the rendercopy case which uses 3D pipeline.
However media pipeline is simpler than 3D pipeline and there is few changes
between gen6,gen7 and gen8
Reviewed-by: Zhao Yakui <yakui.zhao@intel.com>
Signed-off-by: Xiang, Haihao <haihao.xiang@intel.com>
Since we now always want a length for this command, and we've created a
non-length variant, remove the #define to prevent further foot shooting.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
I've opted to not use the PIPE_CONTROL w/a for now. I am unclear if it
is actually required (the test does pass).
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
The extra parameter is for future platform.
Signed-off-by: Chon Ming Lee <chon.ming.lee@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
to not run out of filedescs as some tests call gem_quiescent_gpu
directly.
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Various C library implementations have various races with regards
to caching getpid() or TID inside pthread_kill() implementations.
For example see clone(2) glibc man page and pthread_kill
Bionic C library source.
Work around that by making sure correct PID/TGID and TID values
are retrieved from the kernel when re-raising the signal. It
can be delivered immediately after the clone system call while C
library cached copies have not yet been updated.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tests depend on assertions being enabled since they can, and do,
contain actual test steps. They are also mandatory for ensuring
sane test case behaviour.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Android apparently compiles with NDEBUG. Which is strongly advised
against, since the big pile of asserts mostly check correct usage of
the helper code in testcases.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
rendercopy does the batch buffer flush internally, so if we want
to use it with multiple contexts, we need to pass the context
in from caller.
v2: Modify rendercopy_gen8 as well
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
This way the igt test will always be killed first (hopefully),
preventing mayhem when one of the memory thrashing tests treatens to
take down the entire system.
To avoid any burden on test writers we adjust the oom score on
drm_open, any of the fork helpers and subtest init. That should cover
everything.
v2: Fix it up.
Cc: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
PLANE_A/PLANE_B are used by libdrm's i915_drm.h in Android.
v2: Changes suggested by Daniel Vetter and Damien Lespiau:
- Pimp up comment with a FIXME.
- Reword commit message.
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As these files are compiled for every test, the warnings cluttered
the Android build completely.
v2: As suggested by Daniel Vetter, drop some of the fixes and fix
the compilation flags instead.
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Move scratch_buf_write_to_png() to its only user, gem_render_copy.c.
This makes the cairo dependencies easier to handle from the Android
perspective, but if there is a good reason why this file exists I can
try to handle it differently.
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This makes cairo dependencies easier to handle. Otherwise, we
would have to litter drmtest all over with "#ifndef ANDROID"
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
[danvet: Add missing _GNU_SOURCE to igt_kms.c and missing include to
intel_sprite_on.c]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In this way, all source files are listed in Makefile.sources and included
from Makefile.am, thus enabling the reuse from Android makefiles.
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This will hopefully help debugging things.
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
For posterity, I've squashed these commits against Damien's request.
rendercopy/gen8: Fix the include guards
rendercopy/gen8: Update the 3DSTATE_MULTISAMPLE opcode
The opcode has changed in BDW.
rendercopy/gen8: Add the VF_TOPOLOGY state
The primitive type has moved out of the 3DPRIMITIVE to its own state,
VF_TOPOLOGY.
rendercopy/gen8: Fixup 3STATE_PS
Update the state to the latest BSpec, in particular the thread count was
using a wrong shift and we were missing kernel2 offset.
rendercopy/gen8: Update 3DSTATE_BASE_ADDRESS
This state has seen its fields moved around a bit, follow the BSpec.
rendercopy/gen8: Allocate 64 VUEs
The simulator screams at us if we try to allocate less than that.
rendercopy/gen8: Surface states have to be 64 bytes a aligned
rendercopy/gen8: Vertical/horizontal align 2 does not exist any more
So set them to 4. This should not matter with rendercopy (which is not
using compressed textures), but it makes the simulator moan.
rendercopy/gen8: Make sure the vertex buffer is 8 bytes aligned
rendercopy/gen8: Adjust 3DSTATE_VERTEX_BUFFERS for gen8
The address of the buffer is now on 48 bits. Also the size was computed
as offset + size where the field is really the size of the buffer
itself, not the end address.
rendercopy/gen8: Update the SF/SBE states for gen8
gen8 has a few changes around those states and a new ones RASTER and
SBE_SWIZ.
rendercopy/gen8: Add the PS_EXTRA and PS_BLEND states
rendercopy/gen8: Fix building with DEBUG_RENDERCOPY defined
The forward declaration was missing the final ';'. Let's move the whole
function at the top instead.
rendercopy/gen8: Update the PS and CONSTANT_PS states
rendercopy/gen8: Fix the red channel selection
Make it output red.
rendercopy/gen8: Update the write -1 shader
With the latest assembler changes from Haihao.
rendercopy/gen8: Remove blit.g8a
There is no diff between this file and blig.g7a. Remove it.
rendercopy/gen8: Fix the surface relocation offset
The surface base address is now at dwords 8/9 so the relocation has to
mirror the change.
rendercopy/gen8: Add the VF_INSTANCING state
Should work without, but doesn't hurt to add it.
rendercopy/gen8: Set the Attribule enable field in PS_EXTRA
When the SF is set up to output some attributes, the pixel shader also
have to be told there's attributes to care about.
rendercopy/gen8: Set the force bits to read URB offset/length
If we want to override the URB offset/length in the SBE state itself, we
need to set the force bits on (new in gen8)
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
So it gets distributed with make dist.
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
This provides a macro that allows us to update all the arbitrary blit
commands we have stuck throughout the code. It assumes we don't actually
use 64b relocs (which is currently true). This also allows us to easily find
all the areas we need to update later when we really use the upper dword.
This block was done mostly with a sed job, and represents the easier
in test blit implementations.
v2 by Oscar: s/OUT_BATCH/BEGIN_BATCH in BLIT_COPY_BATCH_START
CC: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
