aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd
AgeCommit message (Collapse)AuthorFilesLines
2017-09-28amdgpu/pp: reduce size of vega10_fuses_defaultDave Airlie2-1249/+1238
I've no idea why this is like this, why store 64-bit fields as a string, and then parse the strings, this is just over engineered. Reduce the size of the amdgpu.o by 80k. text data bss dec hex filename 1331332 17982 1008 1350322 149ab2 amdgpu.o 1244668 17982 1008 1263658 13482a amdgpu.o Acked-by: Harry Wentland <[email protected]> Acked-by: Alex Deucer <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu: use designated initialiser for thermal_irq_src.Dave Airlie1-3/+3
This fixes the 0-day build warning. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28amdgpu/pp: slim down the pwr virus tables.Dave Airlie4-20324/+20284
This is what I'd call slightly overengineered, we waste 40k on storing a value that is write or end, when we could just use the register value to denote end. Remove the virus command parameter, and save text data bss dec hex filename 1412724 17982 1008 1431714 15d8a2 ../drm-next-build/drivers/gpu/drm/amd/amdgpu/amdgpu.o 1331332 17982 1008 1350322 149ab2 ../drm-next-build/drivers/gpu/drm/amd/amdgpu/amdgpu.o Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28amdgpu/pp: move amdgpu_fuses_default into static const.Dave Airlie3-5/+3
There is no reason that this gets passed back into the function from outside the file, just reference the table directly. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28amdgpu/pp: move PhwVega10_Magic to static const.Dave Airlie2-2/+1
This isn't used outside this file. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28amdgpu/pp: remove ci_smc/smumgr split.Dave Airlie4-154/+71
This split serves no purpose, and we can make a bunch of functions static now. There are lots of cases of this sort of split in the powerplay code, please start cleaning them up. Ideally the function table is in the same file as all the implementations used in it. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu/vega10: static constify channel_numberDave Airlie1-1/+1
Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu/pp: constify some powerplay tablesDave Airlie1-7/+7
Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28amdgpu/powerplay: constify large structDave Airlie2-4/+4
This moves this from being global data to global rodata, I'm sure it would be easy to move it to being local data. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28amdgpu: don't ask about CHASH just default it for now.Dave Airlie1-1/+2
If we bump this up a level, we can ask about it, for now, just default to what amdgpu does. Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Dave Airlie <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu: map compute rings by least recently used pipeAndres Rodriguez3-10/+28
This patch provides a guarantee that the first n queues allocated by an application will be on different pipes. Where n is the number of pipes available from the hardware. This helps avoid ring aliasing which can result in work executing in time-sliced mode instead of truly parallel mode. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu: add option for force enable multipipe policy for computeAndres Rodriguez3-0/+11
Useful for testing the effects of multipipe compute without recompiling. Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu: use multipipe compute policy on non PL11 asicsAndres Rodriguez1-2/+12
A performance regression for OpenCL tests on Polaris11 had this feature disabled for all asics. Instead, disable it selectively on the affected asics. Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28drm/amdgpu: fix vf error handlingAlex Deucher4-41/+54
The error handling for virtual functions assumed a single vf per VM and didn't properly account for bare metal. Make the error arrays per device and add locking. Reviewed-by: Gavin Wan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-28Merge branch 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie159-8093/+9629
into drm-next First feature pull for 4.15. Highlights: - Per VM BO support - Lots of powerplay cleanups - Powerplay support for CI - pasid mgr for kfd - interrupt infrastructure for recoverable page faults - SR-IOV fixes - initial GPU reset for vega10 - prime mmap support - ttm page table debugging improvements - lots of bug fixes * 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux: (232 commits) drm/amdgpu: clarify license in amdgpu_trace_points.c drm/amdgpu: Add gem_prime_mmap support drm/amd/powerplay: delete dead code in smumgr drm/amd/powerplay: delete SMUM_FIELD_MASK drm/amd/powerplay: delete SMUM_WAIT_INDIRECT_FIELD drm/amd/powerplay: delete SMUM_READ_FIELD drm/amd/powerplay: delete SMUM_SET_FIELD drm/amd/powerplay: delete SMUM_READ_VFPF_INDIRECT_FIELD drm/amd/powerplay: delete SMUM_WRITE_VFPF_INDIRECT_FIELD drm/amd/powerplay: delete SMUM_WRITE_FIELD drm/amd/powerplay: delete SMU_WRITE_INDIRECT_FIELD drm/amd/powerplay: move macros to hwmgr.h drm/amd/powerplay: move PHM_WAIT_VFPF_INDIRECT_FIELD to hwmgr.h drm/amd/powerplay: move SMUM_WAIT_VFPF_INDIRECT_FIELD_UNEQUAL to hwmgr.h drm/amd/powerplay: move SMUM_WAIT_INDIRECT_FIELD_UNEQUAL to hwmgr.h drm/amd/powerplay: add new helper functions in hwmgr.h drm/amd/powerplay: use SMU_IND_INDEX/DATA_11 pair drm/amd/powerplay: refine powerplay code. drm/amd/powerplay: delete dead code in hwmgr.h drm/amd/powerplay: refine interface in struct pp_smumgr_func ...
2017-09-28Merge branch 'drm-fixes-4.14' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie1-1/+188
into drm-fixes A few fixes for 4.14. Nothing too major. * 'drm-fixes-4.14' of git://people.freedesktop.org/~agd5f/linux: drm/radeon: disable hard reset in hibernate for APUs drm/amdgpu: revert tile table update for oland
2017-09-27drm/amdkfd: Improve multiple SDMA queues support per processshaoyunl2-15/+16
HWS does not support over-subscription and the scheduler can not internally modify the engine. Driver needs to program the correct engine ID. Fix the queue and engine selection to create queues on alternating SDMA engines. This allows concurrent bi-directional DMA transfers in a process that creates two SDMA queues. Signed-off-by: shaoyun liu <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-27drm/amdkfd: Limit queue number per process and device to 127Felix Kuehling1-4/+6
HWS uses bit 7 in the queue number of the map process packet for an undocumented feature. Therefore the queue number per process and device must be 127 or less. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-27drm/amdkfd: Clean up process queue managementFelix Kuehling4-14/+8
Removed unused num_concurrent_processes. Implemented counting of queues in QPD. This makes counting the queue list repeatedly in several places unnecessary. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-27drm/amdkfd: Compress unnecessary function parametersYong Zhao4-13/+7
Signed-off-by: Yong Zhao <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-27drm/amdkfd: Improve process termination handlingFelix Kuehling5-81/+200
Separate device queue termination from process queue manager termination. Unmap all queues at once instead of one at a time. Unmap device queues before the PASID is unbound, in the kfd_process_iommu_unbind_callback. When resetting wavefronts in non-HWS mode, do it before the VMID is released. Signed-off-by: Ben Goz <[email protected]> Signed-off-by: shaoyun liu <[email protected]> Signed-off-by: Amber Lin <[email protected]> Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-27drm/amdkfd: Avoid submitting an unnecessary packet to HWSYong Zhao1-12/+14
v2: Make queue mapping interfaces more consistent by passing unmap filter parameters directly to execute_queues_cpsch, same as unmap_queues_cpsch. Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-27drm/amdkfd: Fix MQD updatesFelix Kuehling1-22/+62
When a queue is mapped, the MQD is owned by the FW. The FW overwrites the MQD on the next unmap operation. Therefore the queue must be unmapped before updating the MQD. For the non-HWS case, also fix disabling of queues and creation of queues in disabled state. Signed-off-by: Oak Zeng <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-10-08drm/amdkfd: Pass filter params to unmap_queues_cpschYong Zhao1-11/+9
Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-10-08drm/amdkfd: move locking outside of unmap_queues_cpschYong Zhao1-37/+28
Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-27drm/amdkfd: Avoid name confusion involved in queue unmappingYong Zhao3-35/+35
When unmapping the queues from HW scheduler, there are two actions: reset and preempt. So naming the variables with only preempt is inapproriate. For functions such as destroy_queues_cpsch, what they do actually is to unmap the queues on HW scheduler rather than to destroy them. Change the name to reflect that fact. On the other hand, there is already a function called destroy_queue_cpsch() which exactly destroys a queue, and the name is very close to destroy_queues_cpsch(), resulting in confusion. Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-09-26drm/amdgpu: drop experimental flag for vega10Alex Deucher1-9/+9
Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: fix pflip irq registor for ravenBhawanpreet Lakha1-1/+1
The pflip registor index was incorrect, this was overriding the macro and caused a dummy irq call. Signed-off-by: Bhawanpreet Lakha <[email protected]> Reviewed-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: don't clean-up bottom pipe plane_stateShirish S1-8/+0
In the scenario of setting underlay, dc_validate_global_state() is called after constructing the context with all relevant bottom_pipe related configurations in dm_update_planes_state(). Currently, in dc_validate_global_state(), without checking for bottom_pipe's existence, the pipe_ctx structure is initialised to 0, hence nullyfying the plane_state of bottom_pipe which shall be accessed in populate_initial_data() called from bw_calcs(). Due to this null pointer access kernel panics and leads to reboot when underlay is tried to set. This patch fixes the issue by no longer clearing the top_pipe. This workaround is no longer required. Signed-off-by: Shirish S <[email protected]> Reviewed-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Remove unused dc_validate_guaranteed functionHarry Wentland1-34/+0
It got refactored away and was never cleaned. Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Reduce DC chattinessHarry Wentland2-35/+42
Log DC init but default log level to 0 (default for amdgpu_dc_log) otherwise. Bug reporters can still make DC more chatty by using the dc_log module param. amdgpu.dc_log = 1 v2: Only provide runtime option, no compile time config Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Pass log_mask from DMHarry Wentland6-38/+42
Linux and Windows often desire different log levels. Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amdgpu: Add dc_log module parameterHarry Wentland2-0/+5
We want to make DC less chatty but still allow bug reporters to provide more detailed logs. Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Clean Kconfig formattingHarry Wentland1-5/+5
Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Update include to bring in line with internal treeHarry Wentland2-0/+2
Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Change comments to bring in line with internal treeHarry Wentland2-6/+4
Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Format changes to bring in line with internal treeHarry Wentland3-6/+5
Signed-off-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Disable FBC for linear tilingRoman Li1-0/+4
- Fixing text console on FBC-enabled builds Signed-off-by: Roman Li <[email protected]> Reviewed-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Update DPP registersVitaly Prosyak1-12/+6
Signed-off-by: Vitaly Prosyak <[email protected]> Reviewed-by: Charlene Liu <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Create fake sink if needed when commit streamHarry Wentland2-1/+30
The problem we're trying to fix is this (and similar): 1) X Desktop with single display 2) VT switch 3) Unplug display 4) VT switch back to X 5) re-plug same display Before this we'd fail at step 4 when trying to create a dc_stream_state because of a missing sink. This change will fake a sink in this case. The same scenario applies to S3 resume. Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Andrey Grodzovsky <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Break out amdgpu_dm_connectorHarry Wentland6-103/+146
Stop using amdgpu_connector and roll our own. There is no overlap with amdgpu. Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Andrey Grodzovsky <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Add 2X Cursor Magnification Codepana2-2/+11
Signed-off-by: Pandey, Arun <[email protected]> Reviewed-by: Charlene Liu <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: No need to keep track of unreffed clk sourcesHarry Wentland5-52/+16
This simplifies clock source reprogramming a bit. Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: move dwb registers to header fileYue Hin Lau3-288/+289
Signed-off-by: Yue Hin Lau <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: remove output_format from ipp_setupEric Bernstein6-12/+7
Signed-off-by: Eric Bernstein <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Remove switching of clk sources at end of commitHarry Wentland1-36/+0
This should be taken care of in validate now. All of timing sync is quite broken at the moment anyways. Will submit another patch set to address that. Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Power down clock source at commitHarry Wentland4-21/+46
Still one more in dc_validate_global Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Don't reset clock source at unrefHarry Wentland4-19/+35
Powering down the clock source during unref is unsafe as we might want to unref during atomic_check Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: seperate dpp_cm_helper functions into new fileYue Hin Lau5-155/+330
Signed-off-by: Yue Hin Lau <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-09-26drm/amd/display: Fix context alloc failed loggingAndrew Jiang1-5/+4
Since there was no return statement in the fail block immediately preceding the context_alloc_fail block, any failure within the function caused a context alloc failed error message to be printed. Since the context_alloc_fail block is only used once, move it to where the goto is directly and accompany it with a return statement. Signed-off-by: Andrew Jiang <[email protected]> Reviewed-by: Tony Cheng <[email protected]> Acked-by: Harry Wentland <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.