user/sven/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c, branch v5.9.11

drm/amdgpu: Clean up KFD VMID assignment

2020-07-02T16:02:50Z

The KFD VMID assignment was hard-coded in a few places. Consolidate that in a single variable adev->vm_manager.first_kfd_vmid. The value is still assigned in gmc-ip-version-specific code. Signed-off-by: Felix Kuehling Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdkfd: Put ASIC revision into HSA capability

2020-04-28T15:04:56Z

In order to surface the ASIC revision to user level, we want to put it into the HSA topology. This can be because different ASIC revisions may require user-level software to do different things (e.g. patch code for things that are changed in later hardware revisions). The ASIC revision from the hardware is maximum of 4 bits at this time, so put it into 4 of the open bits in the HSA capability. Then user-level software can use this capability information to know -- for each ASIC -- what revision-based things must be done. Signed-off-by: Joseph Greathouse Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdkfd: Consolidate duplicated bo alloc flags

2020-03-10T19:54:34Z

ALLOC_MEM_FLAGS_* used are the same as the KFD_IOC_ALLOC_MEM_FLAGS_*, but they are interweavedly used in kernel driver, resulting in bad readability. For example, KFD_IOC_ALLOC_MEM_FLAGS_COHERENT is not referenced in kernel, and it functions implicitly in kernel through ALLOC_MEM_FLAGS_COHERENT, causing unnecessary confusion. Replace all occurrences of ALLOC_MEM_FLAGS_* with KFD_IOC_ALLOC_MEM_FLAGS_* to solve the problem. Signed-off-by: Yong Zhao Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdgpu: Use better names to reflect it is CP MQD buffer

2020-03-06T19:34:18Z

Add "CP" to AMDGPU_GEM_CREATE_MQD_GFX9 to indicate it is only for CP MQD buffer. Signed-off-by: Yong Zhao Acked-by: Christian König Signed-off-by: Alex Deucher

drm/amdkfd: Avoid ambiguity by indicating it's cp queue

2020-02-26T19:20:05Z

The queues represented in queue_bitmap are only CP queues. Signed-off-by: Yong Zhao Acked-by: Alex Deucher Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amd: Extend ROCt to surface UUID for devices that have them

2020-02-26T19:18:17Z

Devices from Arcturus onwards will have their UUID exposed to Thunk. Adding neccessary functions to the kernel to propagate the uuid. Signed-off-by: Divya Shikre Signed-off-by: Alex Deucher

drm/amdgpu: Fix check for DPM when returning max clock

2020-02-26T19:17:42Z

pp_funcs may not exist, while dpm may be enabled. This change ensures that KFD topology will report the same as pp_dpm_sclk, as the conditions for reporting them will be the same. Otherwise, we may see the issue where KFD reports "100MHz" in topology as the max speed, while DPM is working correctly. Signed-off-by: Kent Russell Reviewed-by: Alex Deucher Reviewed-by: Evan Quan Signed-off-by: Alex Deucher

drm/amdgpu: Remove kfd eviction fence before release bo (v2)

2020-02-26T19:17:32Z

No need to trigger eviction as the memory mapping will not be used anymore. All pt/pd bos share same resv, hence the same shared eviction fence. Everytime page table is freed, the fence will be signled and that cuases kfd unexcepted evictions. v2: squash in 32 bit fix CC: Christian König CC: Felix Kuehling CC: Alex Deucher Acked-by: Christian König Reviewed-by: Felix Kuehling Signed-off-by: xinhui pan Signed-off-by: Alex Deucher

drm/amdgpu: Improve Vega20 XGMI TLB flush workaround

2020-02-25T16:01:57Z

Using a heavy-weight TLB flush once is not sufficient. Concurrent memory accesses in the same TLB cache line can re-populate TLB entries from stale texture cache (TC) entries while the heavy-weight TLB flush is in progress. To fix this race condition, perform another TLB flush after the heavy-weight one, when TC is known to be clean. Move the workaround into the low-level TLB flushing functions. This way they apply to amdgpu as well, and KIQ-based TLB flush only needs to synchronize once. Signed-off-by: Felix Kuehling Acked-by: Christian König Reviewed-by: shaoyun liu Signed-off-by: Alex Deucher

drm/amdkfd: refactor runtime pm for baco

2020-02-12T21:00:54Z

So far the kfd driver implemented same routines for runtime and system wide suspend and resume (s2idle or mem). During system wide suspend the kfd aquires an atomic lock that prevents any more user processes to create queues and interact with kfd driver and amd gpu. This mechanism created problem when amdgpu device is runtime suspended with BACO enabled. Any application that relies on kfd driver fails to load because the driver reports a locked kfd device since gpu is runtime suspended. However, in an ideal case, when gpu is runtime suspended the kfd driver should be able to: - auto resume amdgpu driver whenever a client requests compute service - prevent runtime suspend for amdgpu while kfd is in use This change refactors the amdgpu and amdkfd drivers to support BACO and runtime power management. Reviewed-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher