Merge tag 'for-5.19-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave...

[J-linux.git] / drivers / gpu / drm / amd / amdgpu / amdgpu_ras.c

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 2de9309a419391ffceb9496ca73a9e5a6fb2a3c7..dac202ae864dd224d14b7975d67dbfce1e9ca3d6 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -197,6 +197,13 @@ static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf,
        if (amdgpu_ras_query_error_status(obj->adev, &info))
                return -EINVAL;
 
        if (amdgpu_ras_query_error_status(obj->adev, &info))
                return -EINVAL;
 

+       /* Hardware counter will be reset automatically after the query on Vega20 and Arcturus */
+       if (obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+           obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+               if (amdgpu_ras_reset_error_status(obj->adev, info.head.block))
+                       dev_warn(obj->adev->dev, "Failed to reset error counter and error status");
+       }
+

        s = snprintf(val, sizeof(val), "%s: %lu\n%s: %lu\n",
                        "ue", info.ue_count,
                        "ce", info.ce_count);
        s = snprintf(val, sizeof(val), "%s: %lu\n%s: %lu\n",
                        "ue", info.ue_count,
                        "ce", info.ce_count);


@@ -550,9 +557,10 @@ static ssize_t amdgpu_ras_sysfs_read(struct device *dev,
        if (amdgpu_ras_query_error_status(obj->adev, &info))
                return -EINVAL;
 
        if (amdgpu_ras_query_error_status(obj->adev, &info))
                return -EINVAL;
 

-       if (obj->adev->asic_type == CHIP_ALDEBARAN) {
+       if (obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+           obj->adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {

                if (amdgpu_ras_reset_error_status(obj->adev, info.head.block))
                if (amdgpu_ras_reset_error_status(obj->adev, info.head.block))

-                       DRM_WARN("Failed to reset error counter and error status");
+                       dev_warn(obj->adev->dev, "Failed to reset error counter and error status");

        }
 
        return sysfs_emit(buf, "%s: %lu\n%s: %lu\n", "ue", info.ue_count,
        }
 
        return sysfs_emit(buf, "%s: %lu\n%s: %lu\n", "ue", info.ue_count,


@@ -1027,9 +1035,6 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
                }
        }
 
                }
        }
 

-       if (!amdgpu_persistent_edc_harvesting_supported(adev))
-               amdgpu_ras_reset_error_status(adev, info->head.block);
-

        return 0;
 }
 
        return 0;
 }
 


@@ -1149,6 +1154,12 @@ int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
                if (res)
                        return res;
 
                if (res)
                        return res;
 

+               if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+                   adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+                       if (amdgpu_ras_reset_error_status(adev, info.head.block))
+                               dev_warn(adev->dev, "Failed to reset error counter and error status");
+               }
+

                ce += info.ce_count;
                ue += info.ue_count;
        }
                ce += info.ce_count;
                ue += info.ue_count;
        }


@@ -1792,6 +1803,12 @@ static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
                        continue;
 
                amdgpu_ras_query_error_status(adev, &info);
                        continue;
 
                amdgpu_ras_query_error_status(adev, &info);

+
+               if (adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 2) &&
+                   adev->ip_versions[MP0_HWIP][0] != IP_VERSION(11, 0, 4)) {
+                       if (amdgpu_ras_reset_error_status(adev, info.head.block))
+                               dev_warn(adev->dev, "Failed to reset error counter and error status");
+               }

        }
 }
 
        }
 }
 


@@ -2278,8 +2295,9 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev)
            !amdgpu_ras_asic_supported(adev))
                return;
 
            !amdgpu_ras_asic_supported(adev))
                return;
 

-       if (!(amdgpu_sriov_vf(adev) &&
-               (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2))))
+       /* If driver run on sriov guest side, only enable ras for aldebaran */
+       if (amdgpu_sriov_vf(adev) &&
+               adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 2))

                return;
 
        if (!adev->gmc.xgmi.connected_to_cpu) {
                return;
 
        if (!adev->gmc.xgmi.connected_to_cpu) {