diff options
| author | Jonathan Kim <jonathan.kim@amd.com> | 2023-03-23 17:17:20 -0400 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-06-09 12:35:31 -0400 |
| commit | 7cee6a6824a0429a6255abe91b5af01b9a01cd03 (patch) | |
| tree | 281a17e83e234f3d62aae716cd640b4620dd3d7e /drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h | |
| parent | 33f3437ae1194ef5dedbf275dcf74ed9c114647d (diff) | |
| download | linux-7cee6a6824a0429a6255abe91b5af01b9a01cd03.tar.gz linux-7cee6a6824a0429a6255abe91b5af01b9a01cd03.tar.bz2 linux-7cee6a6824a0429a6255abe91b5af01b9a01cd03.zip | |
drm/amdgpu: add configurable grace period for unmap queues
The HWS schedule allows a grace period for wave completion prior to
preemption for better performance by avoiding CWSR on waves that can
potentially complete quickly. The debugger, on the other hand, will
want to inspect wave status immediately after it actively triggers
preemption (a suspend function to be provided).
To minimize latency between preemption and debugger wave inspection, allow
immediate preemption by setting the grace period to 0.
Note that setting the preepmtion grace period to 0 will result in an
infinite grace period being set due to a CP FW bug so set it to 1 for now.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h index 2ad708c64012..206f1960857f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_ai.h @@ -584,6 +584,71 @@ struct pm4_mec_release_mem { #endif +#ifndef PM4_MEC_WRITE_DATA_DEFINED +#define PM4_MEC_WRITE_DATA_DEFINED + +enum WRITE_DATA_dst_sel_enum { + dst_sel___write_data__mem_mapped_register = 0, + dst_sel___write_data__tc_l2 = 2, + dst_sel___write_data__gds = 3, + dst_sel___write_data__memory = 5, + dst_sel___write_data__memory_mapped_adc_persistent_state = 6, +}; + +enum WRITE_DATA_addr_incr_enum { + addr_incr___write_data__increment_address = 0, + addr_incr___write_data__do_not_increment_address = 1 +}; + +enum WRITE_DATA_wr_confirm_enum { + wr_confirm___write_data__do_not_wait_for_write_confirmation = 0, + wr_confirm___write_data__wait_for_write_confirmation = 1 +}; + +enum WRITE_DATA_cache_policy_enum { + cache_policy___write_data__lru = 0, + cache_policy___write_data__stream = 1 +}; + + +struct pm4_mec_write_data_mmio { + union { + union PM4_MES_TYPE_3_HEADER header; /*header */ + unsigned int ordinal1; + }; + + union { + struct { + unsigned int reserved1:8; + unsigned int dst_sel:4; + unsigned int reserved2:4; + unsigned int addr_incr:1; + unsigned int reserved3:2; + unsigned int resume_vf:1; + unsigned int wr_confirm:1; + unsigned int reserved4:4; + unsigned int cache_policy:2; + unsigned int reserved5:5; + } bitfields2; + unsigned int ordinal2; + }; + + union { + struct { + unsigned int dst_mmreg_addr:18; + unsigned int reserved6:14; + } bitfields3; + unsigned int ordinal3; + }; + + uint32_t reserved7; + + uint32_t data; + +}; + +#endif + enum { CACHE_FLUSH_AND_INV_TS_EVENT = 0x00000014 }; |
