<html> <head> <meta content="text/html; charset=utf-8" http-equiv="Content-Type"> </head> <body bgcolor="#FFFFFF" text="#000000"> On 25/08/2016 10:08, Chris Wilson wrote: <blockquote cite="mid:20160825090839.9952-12-chris@chris-wilson.co.uk" type="cite"> <pre wrap="">Now that we can wait upon fences before emitting the request, it becomes trivial to wait upon any implicit fence provided by the dma-buf reservation object. Testcase: igt/prime_vgem/fence-wait Signed-off-by: Chris Wilson <a class="moz-txt-link-rfc2396E" href="mailto:chris@chris-wilson.co.uk"><chris@chris-wilson.co.uk></a> --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 104c713ec681..d9b6fe9f7542 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1197,6 +1197,7 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, list_for_each_entry(vma, vmas, exec_list) { struct drm_i915_gem_object *obj = vma->obj; + struct reservation_object *resv; if (obj->flags & other_rings) { ret = eb_sync(obj, req, obj->base.pending_write_domain); @@ -1204,6 +1205,16 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, return ret; } + resv = i915_gem_object_get_dmabuf_resv(obj); + if (resv) { + ret = i915_sw_fence_await_reservation + (&req->submit, resv, &i915_fence_ops, + obj->base.pending_write_domain, + GFP_KERNEL | __GFP_NOWARN); + if (ret < 0) + return ret; + } + if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) i915_gem_clflush_object(obj, false); } </pre> </blockquote> Reviewed-by: John Harrison <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:john.c.harrison@intel.com"><john.c.harrison@intel.com></a> </body> </html>