xref: /openbmc/linux/Documentation/gpu/amdgpu/ras.rst (revision 3ce7547e) 
1====================
2 AMDGPU RAS Support
3====================
4
5The AMDGPU RAS interfaces are exposed via sysfs (for informational queries) and
6debugfs (for error injection).
7
8RAS debugfs/sysfs Control and Error Injection Interfaces
9========================================================
10
11.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
12   :doc: AMDGPU RAS debugfs control interface
13
14RAS Reboot Behavior for Unrecoverable Errors
15============================================
16
17.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
18   :doc: AMDGPU RAS Reboot Behavior for Unrecoverable Errors
19
20RAS Error Count sysfs Interface
21===============================
22
23.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
24   :doc: AMDGPU RAS sysfs Error Count Interface
25
26RAS EEPROM debugfs Interface
27============================
28
29.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
30   :doc: AMDGPU RAS debugfs EEPROM table reset interface
31
32RAS VRAM Bad Pages sysfs Interface
33==================================
34
35.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
36   :doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
37
38Sample Code
39===========
40Sample code for testing error injection can be found here:
41https://cgit.freedesktop.org/mesa/drm/tree/tests/amdgpu/ras_tests.c
42
43This is part of the libdrm amdgpu unit tests which cover several areas of the GPU.
44There are four sets of tests:
45
46RAS Basic Test
47
48The test verifies the RAS feature enabled status and makes sure the necessary sysfs and debugfs files
49are present.
50
51RAS Query Test
52
53This test checks the RAS availability and enablement status for each supported IP block as well as
54the error counts.
55
56RAS Inject Test
57
58This test injects errors for each IP.
59
60RAS Disable Test
61
62This test tests disabling of RAS features for each IP block.
63