drm/xe/pm: Capture errors and handle them

xe_pm_init may encounter failures for various reasons, such as a failure
in initializing drmm_mutex, or when dealing with a d3cold-capable device
for vram_threshold sysfs creation and setting default threshold.
Presently, all these potential failures are disregarded.

Move d3cold.lock initialization to xe_pm_init_early and cause driver
abort if mutex initialization has failed.

For xe_pm_init failures cleanup the driver and return error code

-v2
Make mutex init cleaner (Lucas)

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240412181211.1155732-8-himal.prasad.ghimiray@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

5 files changed, 45 insertions, 21 deletions

diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c
index e47c8ad1bb17..21677b8cd977 100644
--- a/drivers/gpu/drm/xe/xe_device_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
@@ -76,18 +76,14 @@ static void xe_device_sysfs_fini(struct drm_device *drm, void *arg)
 	sysfs_remove_file(&xe->drm.dev->kobj, &dev_attr_vram_d3cold_threshold.attr);
 }
 
-void xe_device_sysfs_init(struct xe_device *xe)
+int xe_device_sysfs_init(struct xe_device *xe)
 {
 	struct device *dev = xe->drm.dev;
 	int ret;
 
 	ret = sysfs_create_file(&dev->kobj, &dev_attr_vram_d3cold_threshold.attr);
-	if (ret) {
-		drm_warn(&xe->drm, "Failed to create sysfs file\n");
-		return;
-	}
-
-	ret = drmm_add_action_or_reset(&xe->drm, xe_device_sysfs_fini, xe);
 	if (ret)
-		drm_warn(&xe->drm, "Failed to add sysfs fini drm action\n");
+		return ret;
+
+	return drmm_add_action_or_reset(&xe->drm, xe_device_sysfs_fini, xe);
 }
diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.h b/drivers/gpu/drm/xe/xe_device_sysfs.h
index 38b240684bee..f9e83d8bd2c7 100644
--- a/drivers/gpu/drm/xe/xe_device_sysfs.h
+++ b/drivers/gpu/drm/xe/xe_device_sysfs.h
@@ -8,6 +8,6 @@
 
 struct xe_device;
 
-void xe_device_sysfs_init(struct xe_device *xe);
+int xe_device_sysfs_init(struct xe_device *xe);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index fa2cc80a08a3..65ea44672cab 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -781,18 +781,26 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		str_yes_no(xe_device_has_sriov(xe)),
 		xe_sriov_mode_to_string(xe_device_sriov_mode(xe)));
 
-	xe_pm_init_early(xe);
+	err = xe_pm_init_early(xe);
+	if (err)
+		return err;
 
 	err = xe_device_probe(xe);
 	if (err)
 		return err;
 
-	xe_pm_init(xe);
+	err = xe_pm_init(xe);
+	if (err)
+		goto err_driver_cleanup;
 
 	drm_dbg(&xe->drm, "d3cold: capable=%s\n",
 		str_yes_no(xe->d3cold.capable));
 
 	return 0;
+
+err_driver_cleanup:
+	xe_pci_remove(pdev);
+	return err;
 }
 
 static void xe_pci_shutdown(struct pci_dev *pdev)
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index 0d5fbd715a25..37fbeda12d3b 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -214,10 +214,21 @@ static void xe_pm_runtime_init(struct xe_device *xe)
 	pm_runtime_put(dev);
 }
 
-void xe_pm_init_early(struct xe_device *xe)
+int xe_pm_init_early(struct xe_device *xe)
 {
+	int err;
+
 	INIT_LIST_HEAD(&xe->mem_access.vram_userfault.list);
-	drmm_mutex_init(&xe->drm, &xe->mem_access.vram_userfault.lock);
+
+	err = drmm_mutex_init(&xe->drm, &xe->mem_access.vram_userfault.lock);
+	if (err)
+		return err;
+
+	err = drmm_mutex_init(&xe->drm, &xe->d3cold.lock);
+	if (err)
+		return err;
+
+	return 0;
 }
 
 /**
@@ -225,23 +236,32 @@ void xe_pm_init_early(struct xe_device *xe)
  * @xe: xe device instance
  *
  * This component is responsible for System and Device sleep states.
+ *
+ * Returns 0 for success, negative error code otherwise.
  */
-void xe_pm_init(struct xe_device *xe)
+int xe_pm_init(struct xe_device *xe)
 {
+	int err;
+
 	/* For now suspend/resume is only allowed with GuC */
 	if (!xe_device_uc_enabled(xe))
-		return;
-
-	drmm_mutex_init(&xe->drm, &xe->d3cold.lock);
+		return 0;
 
 	xe->d3cold.capable = xe_pm_pci_d3cold_capable(xe);
 
 	if (xe->d3cold.capable) {
-		xe_device_sysfs_init(xe);
-		xe_pm_set_vram_threshold(xe, DEFAULT_VRAM_THRESHOLD);
+		err = xe_device_sysfs_init(xe);
+		if (err)
+			return err;
+
+		err = xe_pm_set_vram_threshold(xe, DEFAULT_VRAM_THRESHOLD);
+		if (err)
+			return err;
 	}
 
 	xe_pm_runtime_init(xe);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_pm.h b/drivers/gpu/drm/xe/xe_pm.h
index 119b630ad1d1..18b0613fe57b 100644
--- a/drivers/gpu/drm/xe/xe_pm.h
+++ b/drivers/gpu/drm/xe/xe_pm.h
@@ -20,8 +20,8 @@ struct xe_device;
 int xe_pm_suspend(struct xe_device *xe);
 int xe_pm_resume(struct xe_device *xe);
 
-void xe_pm_init_early(struct xe_device *xe);
-void xe_pm_init(struct xe_device *xe);
+int xe_pm_init_early(struct xe_device *xe);
+int xe_pm_init(struct xe_device *xe);
 void xe_pm_runtime_fini(struct xe_device *xe);
 bool xe_pm_runtime_suspended(struct xe_device *xe);
 int xe_pm_runtime_suspend(struct xe_device *xe);