drm/xe/drm_ras: Add per node cleanup action

cleanup_node_param() is not registered for previous node in case of counter
allocation failure, which results in stale memory of previous node that
isn't cleaned up on unwind. Add per node cleanup action which guarantees
cleanup on unwind and also simplifies the cleanup logic.

Fixes: b40db12b542f ("drm/xe/xe_drm_ras: Add support for XE DRM RAS")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://patch.msgid.link/20260602044919.702209-4-raag.jadav@intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
(cherry picked from commit 67fc5543d8274b2fcbef87734fad0469358f4478)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index 7357100034e2ce0845780375fbe9cad9e623906c..c6cd32b7eeda758c9a73ed6f58d5d617d601aeac 100644 (file)
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -100,53 +100,47 @@ static int assign_node_params(struct xe_device *xe, struct drm_ras_node *node,
        return 0;
 }
 
-static void cleanup_node_param(struct xe_drm_ras *ras, const enum drm_xe_ras_error_severity severity)
+static void cleanup_node_param(struct drm_ras_node *node)
 {
-       struct drm_ras_node *node = &ras->node[severity];
-
-       ras->info[severity] = NULL;
-
        kfree(node->device_name);
        node->device_name = NULL;
 }
 
+static void cleanup_node(struct drm_device *drm, void *node)
+{
+       drm_ras_node_unregister(node);
+       cleanup_node_param(node);
+}
+
 static int register_nodes(struct xe_device *xe)
 {
        struct xe_drm_ras *ras = &xe->ras;
-       int i;
+       struct drm_ras_node *node;
+       int i, ret;
 
        for_each_error_severity(i) {
-               struct drm_ras_node *node = &ras->node[i];
-               int ret;
+               node = &ras->node[i];
 
                ret = assign_node_params(xe, node, i);
-               if (ret) {
-                       cleanup_node_param(ras, i);
-                       return ret;
-               }
+               if (ret)
+                       goto free_param;
 
                ret = drm_ras_node_register(node);
-               if (ret) {
-                       cleanup_node_param(ras, i);
-                       return ret;
-               }
+               if (ret)
+                       goto free_param;
+
+               ret = drmm_add_action_or_reset(&xe->drm, cleanup_node, node);
+               if (ret)
+                       goto null_info;
        }
 
        return 0;
-}
-
-static void xe_drm_ras_unregister_nodes(struct drm_device *device, void *arg)
-{
-       struct xe_device *xe = arg;
-       struct xe_drm_ras *ras = &xe->ras;
-       int i;
-
-       for_each_error_severity(i) {
-               struct drm_ras_node *node = &ras->node[i];
 
-               drm_ras_node_unregister(node);
-               cleanup_node_param(ras, i);
-       }
+free_param:
+       cleanup_node_param(node);
+null_info:
+       ras->info[i] = NULL;
+       return ret;
 }
 
 /**
@@ -175,11 +169,5 @@ int xe_drm_ras_init(struct xe_device *xe)
                return err;
        }
 
-       err = drmm_add_action_or_reset(&xe->drm, xe_drm_ras_unregister_nodes, xe);
-       if (err) {
-               drm_err(&xe->drm, "Failed to add action for Xe DRM RAS (%pe)\n", ERR_PTR(err));
-               return err;
-       }
-
        return 0;
 }