drm/xe/multi_queue: Handle CGP context error

Trigger multi-queue context cleanup upon CGP context error
notification from GuC.

v4: Fix error message

Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20251211010249.1647839-30-niranjana.vishwanathapura@intel.com

5 files changed, 43 insertions, 0 deletions

diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 3e9fbed9cda6..8af3691626bf 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -142,6 +142,7 @@ enum xe_guc_action {
 	XE_GUC_ACTION_REGISTER_CONTEXT_MULTI_QUEUE = 0x4602,
 	XE_GUC_ACTION_MULTI_QUEUE_CONTEXT_CGP_SYNC = 0x4603,
 	XE_GUC_ACTION_NOTIFY_MULTI_QUEUE_CONTEXT_CGP_SYNC_DONE = 0x4604,
+	XE_GUC_ACTION_NOTIFY_MULTI_QUEUE_CGP_CONTEXT_ERROR = 0x4605,
 	XE_GUC_ACTION_CLIENT_SOFT_RESET = 0x5507,
 	XE_GUC_ACTION_SET_ENG_UTIL_BUFF = 0x550A,
 	XE_GUC_ACTION_SET_DEVICE_ENGINE_ACTIVITY_BUFFER = 0x550C,
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 4d5b4ed357cc..3e49e7fd0031 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1618,6 +1618,10 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 	case XE_GUC_ACTION_NOTIFY_MULTI_QUEUE_CONTEXT_CGP_SYNC_DONE:
 		ret = xe_guc_exec_queue_cgp_sync_done_handler(guc, payload, adj_len);
 		break;
+	case XE_GUC_ACTION_NOTIFY_MULTI_QUEUE_CGP_CONTEXT_ERROR:
+		ret = xe_guc_exec_queue_cgp_context_error_handler(guc, payload,
+								  adj_len);
+		break;
 	default:
 		xe_gt_err(gt, "unexpected G2H action 0x%04x\n", action);
 	}
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index d38f5aab0a99..3be5e78485c7 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -48,6 +48,8 @@
 #include "xe_uc_fw.h"
 #include "xe_vm.h"
 
+#define XE_GUC_EXEC_QUEUE_CGP_CONTEXT_ERROR_LEN		6
+
 static struct xe_guc *
 exec_queue_to_guc(struct xe_exec_queue *q)
 {
@@ -3009,6 +3011,35 @@ int xe_guc_exec_queue_reset_failure_handler(struct xe_guc *guc, u32 *msg, u32 le
 	return 0;
 }
 
+int xe_guc_exec_queue_cgp_context_error_handler(struct xe_guc *guc, u32 *msg,
+						u32 len)
+{
+	struct xe_gt *gt = guc_to_gt(guc);
+	struct xe_device *xe = guc_to_xe(guc);
+	struct xe_exec_queue *q;
+	u32 guc_id = msg[2];
+
+	if (unlikely(len != XE_GUC_EXEC_QUEUE_CGP_CONTEXT_ERROR_LEN)) {
+		drm_err(&xe->drm, "Invalid length %u", len);
+		return -EPROTO;
+	}
+
+	q = g2h_exec_queue_lookup(guc, guc_id);
+	if (unlikely(!q))
+		return -EPROTO;
+
+	xe_gt_dbg(gt,
+		  "CGP context error: [%s] err=0x%x, q0_id=0x%x LRCA=0x%x guc_id=0x%x",
+		  msg[0] & 1 ? "uc" : "kmd", msg[1], msg[2], msg[3], msg[4]);
+
+	trace_xe_exec_queue_cgp_context_error(q);
+
+	/* Treat the same as engine reset */
+	xe_guc_exec_queue_reset_trigger_cleanup(q);
+
+	return 0;
+}
+
 /**
  * xe_guc_exec_queue_cgp_sync_done_handler - CGP synchronization done handler
  * @guc: guc
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index ad8c0e8e0415..4d89b2975fe9 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -37,6 +37,8 @@ int xe_guc_exec_queue_memory_cat_error_handler(struct xe_guc *guc, u32 *msg,
 int xe_guc_exec_queue_reset_failure_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_error_capture_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_exec_queue_cgp_sync_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
+int xe_guc_exec_queue_cgp_context_error_handler(struct xe_guc *guc, u32 *msg,
+						u32 len);
 
 struct xe_guc_submit_exec_queue_snapshot *
 xe_guc_exec_queue_snapshot_capture(struct xe_exec_queue *q);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 79a97b086cb2..c9d0748dae9d 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -172,6 +172,11 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_memory_cat_error,
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_exec_queue_cgp_context_error,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_stop,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)