[PATCH 3/3] drm/xe/xe_hw_error: Handle non-fatal errors routed via direct IRQ

[Riana Tauro <riana.tauro@intel.com>]

Process, log and recover non-fatal errors routed via direct IRQ. For errors
that cannot be recovered locally, wedge the device with bus-reset as the
recovery action.

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
---
 drivers/gpu/drm/xe/xe_hw_error.c | 37 ++++++++++++++++++++++++++++----
 1 file changed, 33 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 5a57b7eaebc3..8435c74147ed 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -14,6 +14,7 @@
 #include "xe_drm_ras.h"
 #include "xe_hw_error.h"
 #include "xe_mmio.h"
+#include "xe_ras.h"
 #include "xe_survivability_mode.h"
 
 #define GT_HW_ERROR_MAX_ERR_BITS		16
@@ -165,11 +166,38 @@ static_assert(ARRAY_SIZE(pvc_master_local_nonfatal_err_reg) == XE_RAS_REG_SIZE);
 						 pvc_master_local_fatal_err_reg : \
 						 pvc_master_local_nonfatal_err_reg)
 
+static const char *hw_err_to_str(const enum hardware_error hw_err)
+{
+	switch (hw_err) {
+	case HARDWARE_ERROR_CORRECTABLE:
+		return "Correctable";
+	case HARDWARE_ERROR_NONFATAL:
+		return "Non-Fatal";
+	case HARDWARE_ERROR_FATAL:
+		return "Fatal";
+	default:
+		return "Unknown";
+	}
+}
+
 static void hw_error_work(struct work_struct *work)
 {
 	struct xe_tile *tile = container_of(work, typeof(*tile), hw_error_work);
 	struct xe_device *xe = tile_to_xe(tile);
 
+	if (xe->info.has_sysctrl) {
+		int ret;
+
+		ret = xe_ras_process_errors(xe);
+		/* For any non-fatal errors that do not return recovered, declare wedged */
+		if (ret) {
+			xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_BUS_RESET);
+			xe_device_declare_wedged(xe);
+		}
+
+		return;
+	}
+
 	xe_survivability_mode_runtime_enable(xe);
 }
 
@@ -431,12 +459,13 @@ static void hw_error_source_handler(struct xe_tile *tile, const enum hardware_er
 		return;
 
 	/*
-	 * Hardware errors are reported through System Controller on the platforms that
-	 * support it, and never routed as direct IRQ to SGUnit. So we should never be
-	 * here for those platforms.
+	 * Non fatal errors are routed as a direct IRQ on platforms that support
+	 * system controller.
 	 */
 	if (xe->info.has_sysctrl) {
-		drm_err_ratelimited(&xe->drm, HW_ERR "Invalid error routing\n");
+		drm_err_ratelimited(&xe->drm, HW_ERR "%s %s reported\n", hw_err_to_str(hw_err),
+				    severity_str);
+		schedule_work(&tile->hw_error_work);
 		return;
 	}
 
-- 
2.47.1