The kernel_context does not use initial-breadcrumbs, so when we ask if its requests have started we do so by comparing against the completion seqno of the previous request. This is very imprecise, not precise enough for the defer_request assertion. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1847 Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> --- drivers/gpu/drm/i915/gt/intel_lrc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 400b9b5a6882..28b477f531a5 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1886,7 +1886,8 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) continue; /* No waiter should start before its signaler */ - GEM_BUG_ON(i915_request_started(w) && + GEM_BUG_ON(w->context->timeline->has_initial_breadcrumb && + i915_request_started(w) && !i915_request_completed(rq)); GEM_BUG_ON(i915_request_is_active(w)); -- 2.20.1 _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
