[PATCH V2] drm/amdgpu: sysfs node disable query error count during gpu reset

YiPeng Chai YiPeng.Chai at amd.com
Mon Jul 1 03:19:21 UTC 2024


Sysfs node disable query error count during gpu reset.

Signed-off-by: YiPeng Chai <YiPeng.Chai at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index ac7ded01dad0..a65b5197b0fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -619,6 +619,7 @@ static const struct file_operations amdgpu_ras_debugfs_eeprom_ops = {
 static ssize_t amdgpu_ras_sysfs_read(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	int ret;
 	struct ras_manager *obj = container_of(attr, struct ras_manager, sysfs_attr);
 	struct ras_query_if info = {
 		.head = obj->head,
@@ -627,7 +628,10 @@ static ssize_t amdgpu_ras_sysfs_read(struct device *dev,
 	if (!amdgpu_ras_get_error_query_ready(obj->adev))
 		return sysfs_emit(buf, "Query currently inaccessible\n");
 
-	if (amdgpu_ras_query_error_status(obj->adev, &info))
+	ret = amdgpu_ras_query_error_status(obj->adev, &info);
+	if (ret == -EIO) /* gpu reset is ongoing */
+		return sysfs_emit(buf, "Query currently inaccessible\n");
+	else if (ret)
 		return -EINVAL;
 
 	if (amdgpu_ip_version(obj->adev, MP0_HWIP, 0) != IP_VERSION(11, 0, 2) &&
@@ -1290,12 +1294,19 @@ static int amdgpu_aca_log_ras_error_data(struct amdgpu_device *adev, enum amdgpu
 ssize_t amdgpu_ras_aca_sysfs_read(struct device *dev, struct device_attribute *attr,
 				  struct aca_handle *handle, char *buf, void *data)
 {
+	int ret;
 	struct ras_manager *obj = container_of(handle, struct ras_manager, aca_handle);
 	struct ras_query_if info = {
 		.head = obj->head,
 	};
 
-	if (amdgpu_ras_query_error_status(obj->adev, &info))
+	if (!amdgpu_ras_get_error_query_ready(obj->adev))
+		return sysfs_emit(buf, "Query currently inaccessible\n");
+
+	ret = amdgpu_ras_query_error_status(obj->adev, &info);
+	if (ret == -EIO) /* gpu reset is ongoing */
+		return sysfs_emit(buf, "Query currently inaccessible\n");
+	else if (ret)
 		return -EINVAL;
 
 	return sysfs_emit(buf, "%s: %lu\n%s: %lu\n%s: %lu\n", "ue", info.ue_count,
-- 
2.34.1



More information about the amd-gfx mailing list