aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2021-03-23drm/amd/pm: Add atom_smc_dpm_info_v4_10 for aldebaranLijo Lazar2-0/+75
Add atom_smc_dpm_info_v4_10 that defines board parameters for aldebaran Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Kenneth Feng <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: Don't do FB resize under A+A configOak Zeng1-1/+2
Disable PCIe BAR resizing on A+A config. It's not needed because we won't use the PCIe BAR, but it breaks the PCI BAR configuration with the current SBIOS. Error message of FB BAR resize failure under A+A: [ 154.913731] [drm:amdgpu_device_resize_fb_bar [amdgpu]] *ERROR* Problem resizing BAR0 (-22). Signed-off-by: Oak Zeng <[email protected]> Reviewed-by: Amber Lin <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Reviewed-by: Christian Koenig <[email protected]> Tested-by: Amber Lin <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: pre-map device buffer as cached for A+A configOak Zeng1-2/+7
For A+A configuration, device memory is supposed to be mapped as cachable from CPU side. For kernel pre-map gpu device memory using ioremap_cache Signed-off-by: Oak Zeng <[email protected]> Reviewed-by: Christian Koenig <[email protected]> Tested-by: Amber Lin <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: update atom_firmware_info_v3_4 (v2)Feifei Xu2-1/+6
v1: Added some pspbl parameters v2: fix fallthrough issue Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: Lazar Lijo <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amd/pm:add aldebaran support for getting bootup valuesFeifei Xu1-1/+15
for SMU config. Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: disallow use semaphore on aldebaranHawking Zhang1-0/+7
shall revisit the change later Signed-off-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: switch to vega20 ih block for aldebaranHawking Zhang1-2/+2
replace vega10 ih block with vega20 ih block for aldebaran. Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: correct IH_CHICKEN programming for aldebaranHawking Zhang1-0/+15
For aldebaran, psp firmware won't program IH_CHICKEN. it now depends on driver to program it properly so either bus address or gpu virtual address is just working for ih ring. Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: add mmhub error status query callback for aldebaranHawking Zhang1-0/+27
The callback will be invoked to query mmea error status when needed. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Dennis Li<[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: add mmhub ras error reset callback for aldebaranHawking Zhang1-0/+12
The callback will be invoked to reset mmhub ras error counters when needed. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Dennis Li<[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: add mmhub ras error query callback for aldebaranHawking Zhang1-51/+689
The callback will be invoked to harvest all kinds of mmhub ras error Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Dennis Li<[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: add sdma ras error reset callback for aldebaranHawking Zhang1-0/+17
The callback will be invoked to reset sdma ras error counters when needed. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Dennis Li<[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: add sdma ras error query callback for aldebaranHawking Zhang1-0/+187
The callback will be invoked to harvest all kinds of sdma ras error Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Dennis Li<[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: add sdma v4_4 ras functionHawking Zhang4-0/+61
sdma ras function is the main structure to support sdma ras on aldebaran. the patch initializes late_init late_fini callbacks. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Dennis Li<[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: apply sdma golden settings for aldebaranHawking Zhang1-0/+18
perform one-time initialization for sdma registers Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: use physical_node_id to calculate aper_baseHawking Zhang1-12/+6
Similar as xgmi connected gpu nodes, physical_node_id * segment_size should be used to calculate the offset of aper_base. The asic type check is redundant. once physical_node_id and segment_size are initialized, it should be count on. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: skip gds ras workaround for aldebaranHawking Zhang1-1/+2
there won't be any gds useage in either kernel or pm4 anymore for aldebaran. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: init gds for aldebaranHawking Zhang1-0/+10
aldebaran removed gds internal memory for atomic usage. it only supports gws opcode in kernel like barrier, semaphore.etc. there won't be usage of gds in either kernel or pm4 packet. max_wave_id should also be marked as deprecated for aldebaran. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: correct vram_info for HBM2EFeifei Xu1-2/+2
correct atom_vram_info_header_v2_6 and its vram_module. Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: support get_vram_info atomfirmware i/f for aldebaranHawking Zhang2-0/+37
Query vram_type, channel_num, channel_width information through atomfirmware i/f Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu:return true for mode1_reset_support on aldebaranFeifei Xu1-0/+3
Will remove once validation finished. Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu:add smu mode1/2 support for aldebaranFeifei Xu11-82/+164
Use MSG_GfxDriverReset for mode reset and retire MSG_Mode1Reset. Centralize soc15_asic_mode1_reset() and nv_asic_mode1_reset()functions. Add mode2_reset_is_support() for smu->ppt_funcs. Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: Add DID for aldebaranFeifei Xu1-0/+5
Add 0x7408,0x740C,0x740F in pciidlist. Signed-off-by: Feifei Xu <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: added support for register list loading (v2)John Clements1-0/+28
call host to psp cmd to load reg list v2: update to latest interface (Alex) Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: added register list driver ctx (v2)John Clements3-0/+8
updated psp bin parsing and load register list v2: update to latest interface (Alex) Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: updated host to psp mailbox cmd (v2)John Clements1-0/+1
added host to psp cmd for register list v2: update to new interface (Alex) Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: John Clements <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: declare smuio v13_0 callbacks as staticHawking Zhang1-2/+2
fix -Wmissing-protoypes warning Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Likun Gao <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: initialize external rev_id for aldebaranHawking Zhang1-0/+1
add exteranal rev_id for aldebaran Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: declare sdma firmware binary file for aldebaranKevin Wang1-0/+1
declare sdma firmware binary file for aldebaran Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amd/swsmu: add aldebaran smu13 ip support (v3)Kevin Wang12-5/+3797
Add initial swSMU support. v1: add smu13 ip support for aldebaran asic (Kevin/Kenneth) v2: switch to thm/mp v13_0 ip headers (Hawking) v3: squash in updates (Alex) Signed-off-by: Kevin Wang <[email protected]> Signed-off-by: Kenneth Feng <[email protected]> Reviewed-by: Kenneth Feng <[email protected]> Signed-off-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amd/swsmu: add aldebaran smu driver if header (v2)Kevin Wang1-0/+512
add aldebaran smu13 driver if header v2: squash in updates Signed-off-by: Kevin Wang <[email protected]> Signed-off-by: Kenneth Feng <[email protected]> Reviewed-by: Kenneth Feng <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: comments out vcn/jpeg ip blocks for aldebaranHawking Zhang1-2/+2
vcn fw front door loading is not functional. comments out vcn/jpeg ip blocks so people can load amdgpu driver without specify ip_mask module parameter. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Reviewed-by: James Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: initialize ta firmware for aldebaranHawking Zhang1-0/+5
only xgmi ta is supported at this stage Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Kevin Wang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: switch to use reg distance member for mmhub v1_7Kevin Wang1-15/+29
switch to use register distance member for mmhub v1_7 instead of hardcode Signed-off-by: Kevin Wang <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: Clean up mmhub functions for aldebaranOak Zeng3-34/+18
Add more function pointers to amdgpu_mmhub_funcs. ASIC specific implementation of most mmhub functions are called from a general function pointer, instead of calling different function for different ASIC. V2: Split patch into upstreamable and aldebaran Signed-off-by: Oak Zeng <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Rajneesh Bhardwaj <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu/jpeg: enable JPEG on aldebaranJames Zhu1-0/+1
enable JPEG on aldebaran Signed-off-by: James Zhu <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu/vcn: enable VCN on aldebaranJames Zhu1-0/+2
Enable VCN on aldebaran Signed-off-by: James Zhu <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu/nbio: add aldebaran supportJames Zhu1-3/+17
Aldebaran has a new mmBIF_MMSCH1_DOORBELL_RANGE setting. Signed-off-by: James Zhu <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: skip MEC2_JT initialization for aldebaranHawking Zhang1-2/+3
MEC2_JT is not supported Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Le Ma <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdkfd: add new flag for uncached GPU mappingEric Huang1-0/+1
The macro is for memory mapped by GPU as uncached. Signed-off-by: Eric Huang <[email protected]> Reviewed-by: Oak Zeng <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: new cache coherence change for AldebaranEric Huang2-2/+31
To support new cache coherence HW on A+A platform mainly in KFD. Signed-off-by: Eric Huang <[email protected]> Reviewed-by: Oak Zeng <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu/jpeg2.6: Add jpeg2.6 supportJames Zhu2-2/+64
Aldebaran is using jpeg2.6, and the main change is jpeg2.6 using AMDGPU_MMHUB_0, and jpeg2.5 using AMDGPU_MMHUB_1. Signed-off-by: James Zhu <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: Fix an omission when adding Aldebaran supportYong Zhao1-1/+2
Aldebaran should be the same as Arcturus in the PTE SNOOPED bit handling. Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: Fix IH client ID naming tableOak Zeng2-0/+2
Client ID 26 is reserved. Add it to the table. Signed-off-by: Oak Zeng <[email protected]> Reviewed-by: Le Ma <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu/vcn2.6: Add vcn2.6 supportJames Zhu2-2/+98
Aldebaran is using vcn2.6, and the main change is vcn2.6 using AMDGPU_MMHUB_0, and vcn2.5 using AMDGPU_MMHUB_1 Signed-off-by: James Zhu <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: add Aldebaran to the VCN familyJames Zhu1-0/+5
including firmware support etc. Signed-off-by: James Zhu <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdkfd: expose host gpu link via sysfs (v2)Rajneesh Bhardwaj1-1/+15
Currently host-gpu io link is always reported as PCIe however, on some A+A systems, there could be one xgmi link available. This change exposes xgmi link via sysfs when it is present. v2: fix includes (Alex) Reviewed-by: Oak Zeng <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Rajneesh Bhardwaj <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: support get xgmi information for AldebaranRajneesh Bhardwaj1-11/+47
Aldebaran uses registers defined in header gc_9_4_2 but much of the xgmi related functionality can be obtained by reusing the exisitng definition from gfxhub_v1_1_get_xgmi_info. While adding support for Aldebaran, also refactored code to better handle the new scenario. Signed-off-by: Rajneesh Bhardwaj <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: define address map for host xgmi link (v3)Rajneesh Bhardwaj3-5/+35
This applies to AMD Accelerated Processing Platforms that support host gpu interconnect throguh a special link (xgmi). Aldebaran systems will support this special feature for utilizing the benefits of host-gpu cache coherence. This change outlines the basic framework for mapping the GPU VRAM (HBM) to system address space making it accesible to the host but managed by the amdgpu driver since this region is marked as reserved memory in host address space by the underlying system firmware. v2: switch to smuio callback function to check the type of host-gpu interface (Hawking) v3: use hub callbacks rather than direct function calls (Alex) Reviewed-by: Oak Zeng <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Rajneesh Bhardwaj <[email protected]> Signed-off-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-03-23drm/amdgpu: enable xgmi support for AldebaranRajneesh Bhardwaj1-1/+3
Like its predecessors Aldebran also supports advanced high bandwidth GPU-GPU communication interface known as xgmi. This enables the basic xgmi support while refactoring the code slightly. Detection of xgmi link between host cpu and gpu will be introduced in a different patch. Reviewed-by: Oak Zeng <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Rajneesh Bhardwaj <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.