summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
Commit message (Collapse)AuthorAgeFilesLines
* drm/amdkfd: use map_queues for hiq on gfx v10 as wellHuang Rui2020-01-161-21/+61
| | | | | | | | To align with gfx v9, we use the map_queues packet to load hiq MQD. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdgpu: flush TLB functions removal from kfd2kgd interfaceAlex Sierra2020-01-161-67/+0
| | | | | | | | | | | | | | | [Why] kfd2kgd interface will be deprecated. This removal only covers TLB invalidation for now. They have been replaced in amdgpu_amdkfd API. [How] TLB invalidate functions removed from the different amdkfd_gfx_v* versions. Signed-off-by: Alex Sierra <alex.sierra@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Delete unnecessary pr_fmt switchYong Zhao2019-10-301-3/+0
| | | | | | | | | Given amdkfd.ko has been merged into amdgpu.ko, this switch is no longer useful. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Use array to probe kfd2kgd_callsYong Zhao2019-10-031-6/+1
| | | | | | | | | This is the same idea as the kfd device info probe and move all the probe control together for easy maintenance. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Delete unnecessary function declarationsYong Zhao2019-10-031-85/+30
| | | | | | | | | Ajust the function sequences so that those function delcarations are not needed any more. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdgpu: Delete useless header file referenceYong Zhao2019-10-031-6/+0
| | | | | | | | Those header file includes are not needed. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Use setup_vm_pt_regs function from base driver in KFDYong Zhao2019-10-031-20/+3
| | | | | | | | This was done on GFX9 previously, now do it for GFX10. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Eliminate get_atc_vmid_pasid_mapping_validYong Zhao2019-10-031-30/+19
| | | | | | | | | | | | | get_atc_vmid_pasid_mapping_valid() is very similar to get_atc_vmid_pasid_mapping_pasid(), so they can be merged into a new function get_atc_vmid_pasid_mapping_info() to reduce register access times. More importantly, getting the PASID and the valid bit atomically with a single read fixes some potential race conditions where the mapping changes between the two reads. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Use better name for sdma queue non HWS pathYong Zhao2019-10-031-47/+45
| | | | | | | | | | The old name is prone to confusion. The register offset is for a RLC queue rather than a SDMA engine. The value is not a base address, but a register offset. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Delete useless SDMA register setting on non HWS pathYong Zhao2019-10-031-8/+1
| | | | | | | | | HW folks have confirm that we should not touch RESUME_CTX of SDMA*_GFX_CONTEXT_CNTL when manipulating RLC queues. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Sync gfx10 kfd2kgd_calls function pointersYong Zhao2019-10-031-2/+3
| | | | | | | | get_hive_id was not set. Also, adjust the function setting sequence. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd: Add an error print if SDMA RLC is not idleYong Zhao2019-10-031-2/+6
| | | | | | | | The message will be useful when troubleshooting the issues. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdkfd/gfx10: Calling amdgpu functions to invalidate TLBOak Zeng2019-08-151-38/+3
| | | | | | | | | | Calling amdgpu function to invalidate TLB, instead of using a kfd implementation. Delete the kfd local TLB invalidation implementation. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Reviewed-by: Christian Konig <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdgpu: drop drmP.h from amdgpu_amdkfd_gfx_v10.cAlex Deucher2019-07-311-1/+0
| | | | | | | Unused. Acked-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/amdgpu: Add navi10 kfd support for amdgpu (v3)Hawking Zhang2019-06-211-0/+975
KFD (Kernel Fusion Driver) is the compute backend driver for AMD GPUs. v2: squash in updates (Alex) v3: fix warnings (Alex) Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Signed-off-by: Philip Cox <Philip.Cox@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
OpenPOWER on IntegriCloud