drm/amd/ras: Support high-frequency querying sriov ras block error count

Browse source

Support high-frequency querying sriov ras block error count:
1. Create shared memory and fills it with RAS_CMD__GET_LAL_LOC_STATUS
   ras command.
2. The RAS_CMD_GET_ALL_BLOCK_ECC_STATUS command and shared
   memory are registered to sriov host ras auto-update list
   via RAS_CMD_SET_CMD_AUTO_UPDATE command.
3. Once sriov host detects ras error, it will automatically execute
   RAS_CMD__GET_ALL_BLOCK_ECC_STATUS command and write the result to
   shared memory.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

...

This commit is contained in:

YiPeng Chai 2025-10-30 16:06:25 +08:00 • committed by Alex Deucher

parent fcfa8dbb08

commit 11dcf72eb5

3 changed files with 154 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

112

drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_virt_ras_cmd.c

View file

9

drivers/gpu/drm/amd/ras/ras_mgr/amdgpu_virt_ras_cmd.h

View file

33

drivers/gpu/drm/amd/ras/rascore/ras_cmd.h

View file