[PATCH v8 1/4] drm/xe: Validate wedged_mode parameter and define enum for modes
Lukasz Laguna
lukasz.laguna at intel.com
Thu Jul 31 12:37:53 UTC 2025
Check correctness of the wedged_mode parameter input to ensure only
supported values are accepted. Additionally, replace magic numbers with
a clearly defined enum.
Signed-off-by: Lukasz Laguna <lukasz.laguna at intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko at intel.com>
---
v7: Rename xe_device_wedged_mode_to_string to xe_wedged_mode_to_string
(Michal)
Split complex condition into smaller, separate ones (Michal)
---
drivers/gpu/drm/xe/xe_debugfs.c | 5 +--
drivers/gpu/drm/xe/xe_device.c | 46 ++++++++++++++++++++++++++--
drivers/gpu/drm/xe/xe_device.h | 2 ++
drivers/gpu/drm/xe/xe_device_types.h | 7 ++++-
drivers/gpu/drm/xe/xe_guc_ads.c | 4 +--
drivers/gpu/drm/xe/xe_guc_capture.c | 9 +++++-
drivers/gpu/drm/xe/xe_guc_submit.c | 7 +++--
drivers/gpu/drm/xe/xe_module.c | 5 +--
drivers/gpu/drm/xe/xe_module.h | 2 +-
9 files changed, 73 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index 0b4a532f7c45..16b2e306559a 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -264,8 +264,9 @@ static ssize_t wedged_mode_set(struct file *f, const char __user *ubuf,
if (ret)
return ret;
- if (wedged_mode > 2)
- return -EINVAL;
+ ret = xe_device_validate_wedged_mode(xe, wedged_mode);
+ if (ret)
+ return ret;
if (xe->wedged.mode == wedged_mode)
return size;
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index c754374f1a8d..f9868b3ddf15 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -749,7 +749,10 @@ int xe_device_probe_early(struct xe_device *xe)
if (err)
return err;
- xe->wedged.mode = xe_modparam.wedged_mode;
+ xe->wedged.mode = xe_device_validate_wedged_mode(xe, xe_modparam.wedged_mode) ?
+ XE_WEDGED_MODE_DEFAULT : xe_modparam.wedged_mode;
+ drm_dbg(&xe->drm, "wedged_mode: setting mode (%u) %s\n",
+ xe->wedged.mode, xe_wedged_mode_to_string(xe->wedged.mode));
err = xe_device_vram_alloc(xe);
if (err)
@@ -1177,7 +1180,7 @@ void xe_device_declare_wedged(struct xe_device *xe)
struct xe_gt *gt;
u8 id;
- if (xe->wedged.mode == 0) {
+ if (xe->wedged.mode == XE_WEDGED_MODE_NEVER) {
drm_dbg(&xe->drm, "Wedged mode is forcibly disabled\n");
return;
}
@@ -1206,3 +1209,42 @@ void xe_device_declare_wedged(struct xe_device *xe)
for_each_gt(gt, xe, id)
xe_gt_declare_wedged(gt);
}
+
+/**
+ * xe_device_validate_wedged_mode - Check if given mode is supported
+ * @xe: the &xe_device
+ * @mode: requested mode to validate
+ *
+ * Check whether the provided wedged mode is supported.
+ *
+ * Return: 0 if mode is supported, error code otherwise.
+ */
+int xe_device_validate_wedged_mode(struct xe_device *xe, unsigned int mode)
+{
+ if (mode > XE_WEDGED_MODE_UPON_ANY_HANG) {
+ drm_dbg(&xe->drm, "wedged_mode: invalid value (%u)\n", mode);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * xe_wedged_mode_to_string - Convert enum value to string.
+ * @mode: the &xe_wedged_mode to convert
+ *
+ * Returns: wedged mode as a user friendly string.
+ */
+const char *xe_wedged_mode_to_string(enum xe_wedged_mode mode)
+{
+ switch (mode) {
+ case XE_WEDGED_MODE_NEVER:
+ return "never";
+ case XE_WEDGED_MODE_UPON_CRITICAL_ERROR:
+ return "upon-critical-error";
+ case XE_WEDGED_MODE_UPON_ANY_HANG:
+ return "upon-any-hang";
+ default:
+ return "<invalid>";
+ }
+}
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index bc802e066a7d..8c780a502374 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -188,6 +188,8 @@ static inline bool xe_device_wedged(struct xe_device *xe)
}
void xe_device_declare_wedged(struct xe_device *xe);
+int xe_device_validate_wedged_mode(struct xe_device *xe, unsigned int mode);
+const char *xe_wedged_mode_to_string(enum xe_wedged_mode mode);
struct xe_file *xe_file_get(struct xe_file *xef);
void xe_file_put(struct xe_file *xef);
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 38c8329b4d2c..1e496845c91f 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -540,7 +540,12 @@ struct xe_device {
/** @wedged.flag: Xe device faced a critical error and is now blocked. */
atomic_t flag;
/** @wedged.mode: Mode controlled by kernel parameter and debugfs */
- int mode;
+ enum xe_wedged_mode {
+ XE_WEDGED_MODE_NEVER = 0,
+ XE_WEDGED_MODE_UPON_CRITICAL_ERROR = 1,
+ XE_WEDGED_MODE_UPON_ANY_HANG = 2,
+ XE_WEDGED_MODE_DEFAULT = XE_WEDGED_MODE_UPON_CRITICAL_ERROR,
+ } mode;
} wedged;
/** @bo_device: Struct to control async free of BOs */
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 8ff8626227ae..c4ea4e6d82ce 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -505,7 +505,7 @@ static void guc_policies_init(struct xe_guc_ads *ads)
ads_blob_write(ads, policies.max_num_work_items,
GLOBAL_POLICY_MAX_NUM_WI);
- if (xe->wedged.mode == 2)
+ if (xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG)
global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET;
ads_blob_write(ads, policies.global_flags, global_flags);
@@ -1054,7 +1054,7 @@ int xe_guc_ads_scheduler_policy_toggle_reset(struct xe_guc_ads *ads)
policies->dpc_promote_time = ads_blob_read(ads, policies.dpc_promote_time);
policies->max_num_work_items = ads_blob_read(ads, policies.max_num_work_items);
policies->is_valid = 1;
- if (xe->wedged.mode == 2)
+ if (xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG)
policies->global_flags |= GLOBAL_POLICY_DISABLE_ENGINE_RESET;
else
policies->global_flags &= ~GLOBAL_POLICY_DISABLE_ENGINE_RESET;
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index 859a3ba91be5..fee57b65b952 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -1856,7 +1856,14 @@ xe_guc_capture_get_matching_and_lock(struct xe_exec_queue *q)
return NULL;
xe = gt_to_xe(q->gt);
- if (xe->wedged.mode >= 2 || !xe_device_uc_enabled(xe) || IS_SRIOV_VF(xe))
+
+ if (xe->wedged.mode == XE_WEDGED_MODE_UPON_ANY_HANG)
+ return NULL;
+
+ if (!xe_device_uc_enabled(xe))
+ return NULL;
+
+ if (IS_SRIOV_VF(xe))
return NULL;
ss = &xe->devcoredump.snapshot;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 751da5cd1d44..a1e79ea66546 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -878,8 +878,9 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
guc_submit_wedged_fini, guc);
if (err) {
- xe_gt_err(gt, "Failed to register clean-up on wedged.mode=2; "
- "Although device is wedged.\n");
+ xe_gt_err(gt, "Failed to register clean-up in wedged.mode=%s; "
+ "Although device is wedged.\n",
+ xe_wedged_mode_to_string(XE_WEDGED_MODE_UPON_ANY_HANG));
return;
}
@@ -894,7 +895,7 @@ static bool guc_submit_hint_wedged(struct xe_guc *guc)
{
struct xe_device *xe = guc_to_xe(guc);
- if (xe->wedged.mode != 2)
+ if (xe->wedged.mode != XE_WEDGED_MODE_UPON_ANY_HANG)
return false;
if (xe_device_wedged(xe))
diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index d9391bd08194..0bf39b78536a 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -10,6 +10,7 @@
#include <drm/drm_module.h>
+#include "xe_device.h"
#include "xe_drv.h"
#include "xe_configfs.h"
#include "xe_hw_fence.h"
@@ -29,7 +30,7 @@
#define DEFAULT_FORCE_PROBE CONFIG_DRM_XE_FORCE_PROBE
#define DEFAULT_MAX_VFS ~0
#define DEFAULT_MAX_VFS_STR "unlimited"
-#define DEFAULT_WEDGED_MODE 1
+#define DEFAULT_WEDGED_MODE XE_WEDGED_MODE_DEFAULT
#define DEFAULT_SVM_NOTIFIER_SIZE 512
struct xe_modparam xe_modparam = {
@@ -88,7 +89,7 @@ MODULE_PARM_DESC(max_vfs,
"[default=" DEFAULT_MAX_VFS_STR "])");
#endif
-module_param_named_unsafe(wedged_mode, xe_modparam.wedged_mode, int, 0600);
+module_param_named_unsafe(wedged_mode, xe_modparam.wedged_mode, uint, 0600);
MODULE_PARM_DESC(wedged_mode,
"Module's default policy for the wedged mode (0=never, 1=upon-critical-errors, 2=upon-any-hang "
"[default=" __stringify(DEFAULT_WEDGED_MODE) "])");
diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h
index 5a3bfea8b7b4..1c75f38ca393 100644
--- a/drivers/gpu/drm/xe/xe_module.h
+++ b/drivers/gpu/drm/xe/xe_module.h
@@ -21,7 +21,7 @@ struct xe_modparam {
#ifdef CONFIG_PCI_IOV
unsigned int max_vfs;
#endif
- int wedged_mode;
+ unsigned int wedged_mode;
u32 svm_notifier_size;
};
--
2.40.0
More information about the Intel-xe
mailing list