kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c, branch v6.18.22

drm/amdgpu: Correct the loss of aca bank reg info

2025-08-27T17:57:47+00:00

By polling, poll ACA bank count to ensure that valid ACA bank reg info can be obtained v2: add corresponding delay before send msg to SMU to query mca bank info (Stanley) v3: the loop cannot exit. (Thomas) v4: remove amdgpu_aca_clear_bank_count. (Kevin) v5: continuously inject ce. If a creation interruption occurs at this time, bank reg info will be lost. (Thomas) v5: each cycle is delayed by 100ms. (Tao) Signed-off-by: Ce Sun Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: handle old RAS eeprom data in non-nps1 mode

2025-05-29T14:57:05+00:00

Get MCA address from PA in nps1, then convert MCA address to PA in specific nps mode. Signed-off-by: ganglxie Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher

drm/amdgpu: Modify the count method of defer error

2025-05-13T13:35:12+00:00

The number of newly added de counts and the number of newly added error addresses remain consistent Signed-off-by: Ce Sun Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: Use active umc info from discovery

2025-02-13T02:02:56+00:00

There could be configs where some UMC instances are harvested. This information is obtained through discovery data and populated in umc.active_mask. Avoid reassigning this as AID mask, instead use the mask directly while iterating through umc instances. This is to avoid accesses to harvested UMC instances. v2: fix warning (Alex) Signed-off-by: Lijo Lazar Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: correct the calculation of RAS bad page

2024-12-10T15:26:51+00:00

After the introduction of NPS RAS, one bad page record on eeprom may be related to 1 or 16 bad pages, so the bad page record and bad page are two different concepts, define a new variable to store bad page number. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: parse legacy RAS bad page mixed with new data in various NPS modes

2024-12-10T15:26:48+00:00

All legacy RAS bad pages are generated in NPS1 mode, but new bad page can be generated in any NPS mode, so we can't use retired_page stored on eeprom directly in non-nps1 mode even for legacy data. We need to take different actions for different data, new data can be identified from old data by UMC_CHANNEL_IDX_V2 flag. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: save UMC global channel index to eeprom

2024-12-10T15:26:46+00:00

Save the global channel index returned by RAS TA to eeprom. We can get memory physical address by MCA address and channel index. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: add function to find all memory pages in one physical row

2024-12-10T15:26:46+00:00

And the function can be reused across amdgpu driver. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: add return value for convert_ras_err_addr

2024-12-10T15:26:46+00:00

So upper layer can return failure directly if address conversion fails. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

drm/amdgpu: reduce memory usage for umc_lookup_bad_pages_in_a_row

2024-12-10T15:26:46+00:00

The function handles one page in one time, allocating umc.retire_unit bad page records is enough. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher