From 3bdc8244e734cff375c70e51b03220787da61eed Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 30 Oct 2019 14:40:09 -0400 Subject: [PATCH 4378/4736] drm/amdgpu: Improve RAS documentation (v2) Clarify some areas, clean up formatting, add section for unrecoverable error handling. v2: fix grammatical errors Reviewed-by: Yong Zhao Signed-off-by: Alex Deucher --- Documentation/gpu/amdgpu.rst | 35 ++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 40 ++++++++++++++++++++----- 2 files changed, 68 insertions(+), 7 deletions(-) diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst index 5b9eaf23558e..0efede580039 100644 --- a/Documentation/gpu/amdgpu.rst +++ b/Documentation/gpu/amdgpu.rst @@ -82,12 +82,21 @@ AMDGPU XGMI Support AMDGPU RAS Support ================== +The AMDGPU RAS interfaces are exposed via sysfs (for informational queries) and +debugfs (for error injection). + RAS debugfs/sysfs Control and Error Injection Interfaces -------------------------------------------------------- .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c :doc: AMDGPU RAS debugfs control interface +RAS Reboot Behavior for Unrecoverable Errors +-------------------------------------------------------- + +.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c + :doc: AMDGPU RAS Reboot Behavior for Unrecoverable Errors + RAS Error Count sysfs Interface ------------------------------- @@ -109,6 +118,32 @@ RAS VRAM Bad Pages sysfs Interface .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c :internal: +Sample Code +----------- +Sample code for testing error injection can be found here: +https://cgit.freedesktop.org/mesa/drm/tree/tests/amdgpu/ras_tests.c + +This is part of the libdrm amdgpu unit tests which cover several areas of the GPU. +There are four sets of tests: + +RAS Basic Test + +The test verifies the RAS feature enabled status and makes sure the necessary sysfs and debugfs files +are present. + +RAS Query Test + +This test checks the RAS availability and enablement status for each supported IP block as well as +the error counts. + +RAS Inject Test + +This test injects errors for each IP. + +RAS Disable Test + +This test tests disabling of RAS features for each IP block. + GPU Power/Thermal Controls and Monitoring ========================================= diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index afc3ee47d1b2..399617932427 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -218,7 +218,7 @@ static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev, * As their names indicate, inject operation will write the * value to the address. * - * Second member: struct ras_debug_if::op. + * The second member: struct ras_debug_if::op. * It has three kinds of operations. * * - 0: disable RAS on the block. Take ::head as its data. @@ -226,14 +226,20 @@ static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev, * - 2: inject errors on the block. Take ::inject as its data. * * How to use the interface? - * programs: - * copy the struct ras_debug_if in your codes and initialize it. - * write the struct to the control node. + * + * Programs + * + * Copy the struct ras_debug_if in your codes and initialize it. + * Write the struct to the control node. + * + * Shells * * .. code-block:: bash * * echo op block [error [sub_block address value]] > .../ras/ras_ctrl * + * Parameters: + * * op: disable, enable, inject * disable: only block is needed * enable: block and error are needed @@ -263,8 +269,10 @@ static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev, * /sys/class/drm/card[0/1/2...]/device/ras/[gfx/sdma/...]_err_count * * .. note:: - * Operation is only allowed on blocks which are supported. + * Operations are only allowed on blocks which are supported. * Please check ras mask at /sys/module/amdgpu/parameters/ras_mask + * to see which blocks support RAS on a particular asic. + * */ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *buf, size_t size, loff_t *pos) @@ -320,7 +328,7 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user * * DOC: AMDGPU RAS debugfs EEPROM table reset interface * * Some boards contain an EEPROM which is used to persistently store a list of - * bad pages containing ECC errors detected in vram. This interface provides + * bad pages which experiences ECC errors in vram. This interface provides * a way to reset the EEPROM, e.g., after testing error injection. * * Usage: @@ -360,7 +368,7 @@ static const struct file_operations amdgpu_ras_debugfs_eeprom_ops = { /** * DOC: AMDGPU RAS sysfs Error Count Interface * - * It allows user to read the error count for each IP block on the gpu through + * It allows the user to read the error count for each IP block on the gpu through * /sys/class/drm/card[0/1/2...]/device/ras/[gfx/sdma/...]_err_count * * It outputs the multiple lines which report the uncorrected (ue) and corrected @@ -1025,6 +1033,24 @@ static int amdgpu_ras_sysfs_remove_all(struct amdgpu_device *adev) } /* sysfs end */ +/** + * DOC: AMDGPU RAS Reboot Behavior for Unrecoverable Errors + * + * Normally when there is an uncorrectable error, the driver will reset + * the GPU to recover. However, in the event of an unrecoverable error, + * the driver provides an interface to reboot the system automatically + * in that event. + * + * The following file in debugfs provides that interface: + * /sys/kernel/debug/dri/[0/1/2...]/ras/auto_reboot + * + * Usage: + * + * .. code-block:: bash + * + * echo true > .../ras/auto_reboot + * + */ /* debugfs begin */ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev) { -- 2.17.1