drm/i915/guc: Fix error capture for virtual engines

GuC based register dumps in error capture logs were basically broken
for virtual engines. This can be seen in igt@gem_exec_balancer@hang:
  [IGT] gem_exec_balancer: starting subtest hang
  [drm] GPU HANG: ecode 12:4:e1524110, in gem_exec_balanc [6388]
  [drm] GT0: GUC: No register capture node found for 0x1005 / 0xFEDC311D
  [drm] GPU HANG: ecode 12:4:00000000, in gem_exec_balanc [6388]
  [IGT] gem_exec_balancer: exiting, ret=0

The test causes a hang on both engines of a virtual engine context.
The engine instance zero hang gets a valid error capture but the
non-instance-zero hang does not.

Fix that by scanning through the list of pending register captures
when a hang notification for a virtual engine is received. That way,
the hang can be assigned to the correct physical engine prior to
starting the error capture process. So later on, when the error capture
handler tries to find the engine register list, it looks for one on
the correct engine.

Also, sneak in a missing blank line before a comment in the node
search code.

v2: Fix null pointer deref on non-GuC platforms.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230428185636.457407-5-John.C.Harrison@Intel.com

1 files changed, 28 insertions, 4 deletions

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index c869ddc73e69..a0e3ef1c65d2 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -4728,13 +4728,37 @@ static void capture_error_state(struct intel_guc *guc,
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct drm_i915_private *i915 = gt->i915;
-	struct intel_engine_cs *engine = __context_to_physical_engine(ce);
 	intel_wakeref_t wakeref;
+	intel_engine_mask_t engine_mask;
+
+	if (intel_engine_is_virtual(ce->engine)) {
+		struct intel_engine_cs *e;
+		intel_engine_mask_t tmp, virtual_mask = ce->engine->mask;
+
+		engine_mask = 0;
+		for_each_engine_masked(e, ce->engine->gt, virtual_mask, tmp) {
+			bool match = intel_guc_capture_is_matching_engine(gt, ce, e);
+
+			if (match) {
+				intel_engine_set_hung_context(e, ce);
+				engine_mask |= e->mask;
+				atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]);
+			}
+		}
+
+		if (!engine_mask) {
+			guc_warn(guc, "No matching physical engine capture for virtual engine context 0x%04X / %s",
+				 ce->guc_id.id, ce->engine->name);
+			engine_mask = ~0U;
+		}
+	} else {
+		intel_engine_set_hung_context(ce->engine, ce);
+		engine_mask = ce->engine->mask;
+		atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]);
+	}
 
-	intel_engine_set_hung_context(engine, ce);
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		i915_capture_error_state(gt, engine->mask, CORE_DUMP_FLAG_IS_GUC_CAPTURE);
-	atomic_inc(&i915->gpu_error.reset_engine_count[engine->uabi_class]);
+		i915_capture_error_state(gt, engine_mask, CORE_DUMP_FLAG_IS_GUC_CAPTURE);
 }
 
 static void guc_context_replay(struct intel_context *ce)