kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h, branch v6.6.132

drm/amdgpu: Update invalid PTE flag setting

2023-07-07T17:51:47+00:00

Update the invalid PTE flag setting with TF enabled. This is to ensure, in addition to transitioning the retry fault to a no-retry fault, it also causes the wavefront to enter the trap handler. With the current setting, the fault only transitions to a no-retry fault. Additionally, have 2 sets of invalid PTE settings, one for TF enabled, the other for TF disabled. The setting with TF disabled, doesn't work with TF enabled. Signed-off-by: Mukul Joshi Acked-by: Christian König Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdgpu: Update total channel number for umc v8_10

2023-06-15T15:06:59+00:00

Update total channel number for umc v8_10. Signed-off-by: Candice Li Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: Override MTYPE per page on GFXv9.4.3 APUs

2023-06-09T13:59:08+00:00

On GFXv9.4.3 NUMA APUs, system memory locality must be determined per page to choose the correct MTYPE. This patch adds a GMC callback that can provide this per-page override and implements it for native mode. Carve-out mode is not yet supported and will use the safe default (remote) MTYPE for system memory. Signed-off-by: Felix Kuehling Reviewed-by: Philip Yang Reviewed-and-tested-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher

drm/amdgpu: Add memory partitions to gmc

2023-06-09T13:57:01+00:00

Some ASICs have the device memory divided into multiple partitions. The parititions could be denoted by a numa node or by a range of pages. Signed-off-by: Lijo Lazar Reviewed-by: Le Ma Signed-off-by: Alex Deucher

drm/amdgpu: Move memory partition query to gmc

2023-06-09T13:56:50+00:00

GMC block handles memory related information, it makes more sense to keep memory partition functions in gmc block. Signed-off-by: Lijo Lazar Reviewed-by: Le Ma Signed-off-by: Alex Deucher

drm/amdgpu: Check APU supports true APP mode

2023-06-09T13:49:05+00:00

On GPXIP 9.4.3 APU, in no carveout mode there is no real vram heap and could be emulated by the driver over the interleaved NUMA system memory and the APU could also be in the carveout mode during early development stage or otherwise for debugging purpose so introduce a new member in amdgpu_gmc to figure out whether the APU is in the native mode as per the production configuration. AMD_IS_APU cannot be used for Accelerated Processing Platform APUs as it might be used in a different context on previous generations or on small APUs. Reviewed-by: Hawking Zhang Reviewed-by: Felix Kuehling Tested-by: Graham Sider Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher

drm/amdgpu: Add XCC inst to PASID TLB flushing

2023-06-09T13:42:46+00:00

Add XCC instance to select the correct KIQ ring when flushing TLBs on a multi-XCC setup. Signed-off-by: Mukul Joshi Tested-by: Amber Lin Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdgpu: Rework retry fault removal

2023-04-13T04:14:24+00:00

Rework retry fault removal from the software filter by storing an expired timestamp for a fault that is being removed. When a new fault comes, and it matches an entry in the sw filter, it will be added as a new fault only when its timestamp is greater than the timestamp expiry of the fault in the sw filter. This helps in avoiding stale faults being added back into the filter and preventing legitimate faults from being handled. Suggested-by: Felix Kuehling Signed-off-by: Mukul Joshi Reviewed-by: Philip Yang Signed-off-by: Alex Deucher

drm/amdgpu: Init MMVM_CONTEXTS_DISABLE in gmc11 golden setting under SRIOV

2023-03-15T22:45:26+00:00

[Why] If disable the mmhub vm contexts(set MMVM_CONTEXTS_DISABLE to 0xffff), driver loading failed on vf due to fence fallback timer expired on all rings. FLR cannot reset MMVM_CONTEXTS_DISABLE. So this vf can not be recovered anymore unless trigger a whole gpu reset. [How] Under SRIOV, init MMVM_CONTEXTS_DISABLE in gmc11 golden register setting. Signed-off-by: Yifan Zha Reviewed-by: Horace Chen Signed-off-by: Alex Deucher

drm/amdgpu: Move umc ras block init to gmc ras sw_init

2023-03-13T21:27:48+00:00

Initialize umc ras block only when umc ip block supports ras. Driver queries ras capabilities after early_init, ras block init needs to be moved to sw_init. Signed-off-by: Hawking Zhang Reviewed-by: Stanley Yang Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher