1. Move xgmi special error inject function from amdgpu_ras.c to xgmi block.
2. Support to use psp_ras_trigger_error as default error inject function in amdgpu_ras.c. If .ras_error_inject isn't defined in ras block, default error inject function will take effect.
Signed-off-by: yipechai <YiPeng.Chai@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 60 +++++-------------------
drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 27 +++++++++++
2 files changed, 39 insertions(+), 48 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index edba3ee292c8..21765e05b003 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1047,32 +1047,6 @@ int amdgpu_ras_reset_error_status(struct amdgpu_device *adev,
return 0;
}
-/* Trigger XGMI/WAFL error */
-static int amdgpu_ras_error_inject_xgmi(struct amdgpu_device *adev,
- struct ta_ras_trigger_error_input *block_info)
-{
- int ret;
-
- if (amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_DISALLOW))
- dev_warn(adev->dev, "Failed to disallow df cstate");
-
- if (amdgpu_dpm_allow_xgmi_power_down(adev, false))
- dev_warn(adev->dev, "Failed to disallow XGMI power down");
-
- ret = psp_ras_trigger_error(&adev->psp, block_info);
-
- if (amdgpu_ras_intr_triggered())
- return ret;
-
- if (amdgpu_dpm_allow_xgmi_power_down(adev, true))
- dev_warn(adev->dev, "Failed to allow XGMI power down");
-
- if (amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_ALLOW))
- dev_warn(adev->dev, "Failed to allow df cstate");
-
- return ret;
-}
-
/* wrapper of psp_ras_trigger_error */
int amdgpu_ras_error_inject(struct amdgpu_device *adev,
struct ras_inject_if *info)
@@ -1091,6 +1065,11 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev,
if (!obj)
return -EINVAL;
+ if (!block_obj || !block_obj->hw_ops) {
+ dev_info(adev->dev, "%s doesn't config ras function \n", get_ras_block_str(&info->head));
+ return -EINVAL;
+ }
+
/* Calculate XGMI relative offset */
if (adev->gmc.xgmi.num_physical_nodes > 1) {
block_info.address =
@@ -1098,30 +1077,15 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev,
block_info.address);
}
- switch (info->head.block) {
- case AMDGPU_RAS_BLOCK__GFX:
- if (!block_obj || !block_obj->hw_ops) {
- dev_info(adev->dev, "%s doesn't config ras function \n", get_ras_block_str(&info->head));
- return -EINVAL;
- }
-
+ 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);
- break;
- case AMDGPU_RAS_BLOCK__UMC:
- case AMDGPU_RAS_BLOCK__SDMA:
- case AMDGPU_RAS_BLOCK__MMHUB:
- case AMDGPU_RAS_BLOCK__PCIE_BIF:
- case AMDGPU_RAS_BLOCK__MCA:
- ret = psp_ras_trigger_error(&adev->psp, &block_info);
- break;
- case AMDGPU_RAS_BLOCK__XGMI_WAFL:
- ret = amdgpu_ras_error_inject_xgmi(adev, &block_info);
- break;
- default:
- dev_info(adev->dev, "%s error injection is not supported yet\n",
- get_ras_block_str(&info->head));
- ret = -EINVAL;
+ } 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);
+ else /*If not defined .ras_error_inject, use default ras_error_inject*/
+ ret = psp_ras_trigger_error(&adev->psp, &block_info);
}
if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index e3c6898c5d13..a2bd3a2abe72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -940,9 +940,36 @@ static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
err_data->ce_count += ce_cnt;
}
+/* Trigger XGMI/WAFL error */
+static int amdgpu_ras_error_inject_xgmi(struct amdgpu_device *adev, void *inject_if)
+{
+ int ret = 0;;
+ struct ta_ras_trigger_error_input *block_info = (struct ta_ras_trigger_error_input *)inject_if;
+
+ if (amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_DISALLOW))
+ dev_warn(adev->dev, "Failed to disallow df cstate");
+
+ if (amdgpu_dpm_allow_xgmi_power_down(adev, false))
+ dev_warn(adev->dev, "Failed to disallow XGMI power down");
+
+ ret = psp_ras_trigger_error(&adev->psp, block_info);
+
+ if (amdgpu_ras_intr_triggered())
+ return ret;
+
+ if (amdgpu_dpm_allow_xgmi_power_down(adev, true))
+ dev_warn(adev->dev, "Failed to allow XGMI power down");
+
+ if (amdgpu_dpm_set_df_cstate(adev, DF_CSTATE_ALLOW))
+ dev_warn(adev->dev, "Failed to allow df cstate");
+
+ return ret;
+}
+
struct amdgpu_ras_block_hw_ops xgmi_ras_hw_ops = {
.query_ras_error_count = amdgpu_xgmi_query_ras_error_count,
.reset_ras_error_count = amdgpu_xgmi_reset_ras_error_count,
+ .ras_error_inject = amdgpu_ras_error_inject_xgmi,
};
struct amdgpu_xgmi_ras xgmi_ras = {
--
2.25.1
