diff options
| author | Tao Zhou <tao.zhou1@amd.com> | 2023-02-27 18:25:23 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-06-09 10:37:10 -0400 |
| commit | 2c22ed0bdb0cb6da9408593eafa6137325576017 (patch) | |
| tree | ff14b3b1ffd44b8ecd787e23841642658bd0082e /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | |
| parent | af2ba368838ee4913e758f34e3d8bbfeb110be36 (diff) | |
drm/amdgpu: add instance mask for RAS inject
User can specify injected instances by the mask. For backward
compatibility, the mask value is incorporated into sub block index
without interface change of RAS TA.
User uses logical mask and driver should convert it to physical value
before sending it to RAS TA.
v2: update parameter name.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 23 |
1 files changed, 16 insertions, 7 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 64f80e8cbd63..7ae08f168f99 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -256,6 +256,8 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, int block_id; uint32_t sub_block; u64 address, value; + /* default value is 0 if the mask is not set by user */ + u32 instance_mask = 0; if (*pos) return -EINVAL; @@ -306,7 +308,11 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, data->op = op; if (op == 2) { - if (sscanf(str, "%*s %*s %*s 0x%x 0x%llx 0x%llx", + if (sscanf(str, "%*s %*s %*s 0x%x 0x%llx 0x%llx 0x%x", + &sub_block, &address, &value, &instance_mask) != 4 && + sscanf(str, "%*s %*s %*s %u %llu %llu %u", + &sub_block, &address, &value, &instance_mask) != 4 && + sscanf(str, "%*s %*s %*s 0x%x 0x%llx 0x%llx", &sub_block, &address, &value) != 3 && sscanf(str, "%*s %*s %*s %u %llu %llu", &sub_block, &address, &value) != 3) @@ -314,6 +320,7 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, data->head.sub_block_index = sub_block; data->inject.address = address; data->inject.value = value; + data->inject.instance_mask = instance_mask; } } else { if (size < sizeof(*data)) @@ -341,7 +348,7 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, * sub_block_index: some IPs have subcomponets. say, GFX, sDMA. * name: the name of IP. * - * inject has two more members than head, they are address, value. + * inject has three more members than head, they are address, value and mask. * As their names indicate, inject operation will write the * value to the address. * @@ -365,7 +372,7 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, * * echo "disable <block>" > /sys/kernel/debug/dri/<N>/ras/ras_ctrl * echo "enable <block> <error>" > /sys/kernel/debug/dri/<N>/ras/ras_ctrl - * echo "inject <block> <error> <sub-block> <address> <value> > /sys/kernel/debug/dri/<N>/ras/ras_ctrl + * echo "inject <block> <error> <sub-block> <address> <value> <mask>" > /sys/kernel/debug/dri/<N>/ras/ras_ctrl * * Where N, is the card which you want to affect. * @@ -382,13 +389,14 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f, * * The sub-block is a the sub-block index, pass 0 if there is no sub-block. * The address and value are hexadecimal numbers, leading 0x is optional. + * The mask means instance mask, is optional, default value is 0x1. * * For instance, * * .. code-block:: bash * * echo inject umc ue 0x0 0x0 0x0 > /sys/kernel/debug/dri/0/ras/ras_ctrl - * echo inject umc ce 0 0 0 > /sys/kernel/debug/dri/0/ras/ras_ctrl + * echo inject umc ce 0 0 0 3 > /sys/kernel/debug/dri/0/ras/ras_ctrl * echo disable umc > /sys/kernel/debug/dri/0/ras/ras_ctrl * * How to check the result of the operation? @@ -1117,13 +1125,14 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, if (info->head.block == AMDGPU_RAS_BLOCK__GFX) { if (block_obj->hw_ops->ras_error_inject) - ret = block_obj->hw_ops->ras_error_inject(adev, info); + ret = block_obj->hw_ops->ras_error_inject(adev, info, info->instance_mask); } else { /* If defined special ras_error_inject(e.g: xgmi), implement special ras_error_inject */ if (block_obj->hw_ops->ras_error_inject) - ret = block_obj->hw_ops->ras_error_inject(adev, &block_info); + ret = block_obj->hw_ops->ras_error_inject(adev, &block_info, + info->instance_mask); else /*If not defined .ras_error_inject, use default ras_error_inject*/ - ret = psp_ras_trigger_error(&adev->psp, &block_info); + ret = psp_ras_trigger_error(&adev->psp, &block_info, info->instance_mask); } if (ret) |