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