On 3/18/2026 12:10 PM, Mallesh Koujalagi wrote:
This handler is designed to be called when power management unit errors are
detected that affect device-level state persisting across warm resets.
Commit message should be clear.
The
cold reset recovery method signals to userspace that only a complete device
power cycle can restore normal operation.
v2:
- Add use case: Handling errors from power management unit,
which requires a complete power cycle (cold reset)
to recover. (Christian)
This is not an addition to the patch. Only add this in cover letter.
Signed-off-by: Mallesh Koujalagi <[email protected]>
---
drivers/gpu/drm/xe/xe_hw_error.c | 27 +++++++++++++++++++++++++++
drivers/gpu/drm/xe/xe_hw_error.h | 1 +
drivers/gpu/drm/xe/xe_ras.c | 3 ++-
3 files changed, 30 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 2a31b430570e..ca965a2b092c 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -5,6 +5,7 @@
#include <linux/bitmap.h>
#include <linux/fault-inject.h>
+#include <drm/drm_drv.h>
#include "regs/xe_gsc_regs.h"
#include "regs/xe_hw_error_regs.h"
@@ -542,6 +543,32 @@ static void process_hw_errors(struct xe_device *xe)
}
}
+/**
+ * xe_punit_error_handler - Handler for power management unit errors
+ * @xe: device instance
+ *
+ * Handles power management unit errors that affect the device and cannot
+ * be recovered through driver reload, PCIe reset, etc.
+ *
+ * Marks the device as wedged with DRM_WEDGE_RECOVERY_COLD_RESET method
+ * and notifies userspace that a complete device power cycle is required.
+ */
+void xe_punit_error_handler(struct xe_device *xe)
You can move this to xe_ras
+{
+ drm_err(&xe->drm, "CRITICAL: PMU error detected\n");
PMU? also means Performance monitoring unit. Please use Punit instead
Keep this consistent in both commit message, kernel-doc and code
+ drm_err(&xe->drm, "Recovery: Device cold reset required\n");
power-cycle/cold-reset. Use consistent wording
Thanks
Riana
+
+ /* Set cold reset recovery method */
+ xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_COLD_RESET);
+
+ if (xe_device_wedged(xe)) {
+ drm_dev_wedged_event(&xe->drm, xe->wedged.method, NULL);
+ } else {
+ /* Declare device wedged - will trigger uevent with cold reset
method */
+ xe_device_declare_wedged(xe);
+ }
+}
+
/**
* xe_hw_error_init - Initialize hw errors
* @xe: xe device instance
diff --git a/drivers/gpu/drm/xe/xe_hw_error.h b/drivers/gpu/drm/xe/xe_hw_error.h
index d86e28c5180c..f588320eb94d 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.h
+++ b/drivers/gpu/drm/xe/xe_hw_error.h
@@ -11,5 +11,6 @@ struct xe_tile;
struct xe_device;
void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl);
+void xe_punit_error_handler(struct xe_device *xe);
void xe_hw_error_init(struct xe_device *xe);
#endif
diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 777321021391..93257d0eaaa0 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -10,6 +10,7 @@
#include "xe_survivability_mode.h"
#include "xe_sysctrl_mailbox.h"
#include "xe_sysctrl_mailbox_types.h"
+#include "xe_hw_error.h"
#define COMPUTE_ERROR_SEVERITY_MASK GENMASK(26, 25)
#define GLOBAL_UNCORR_ERROR 2
@@ -148,7 +149,7 @@ static enum xe_ras_recovery_action
handle_soc_internal_errors(struct xe_device *
xe_err(xe, "[RAS]: PUNIT %s error detected: 0x%x\n",
severity_to_str(xe, common_info.severity),
ieh_error->error_sources_ieh0.punit);
- /** TODO: Add PUNIT error handling */
+ xe_punit_error_handler(xe);
action = XE_RAS_RECOVERY_ACTION_DISCONNECT;
}
}
