Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes: > Let's avoid mixing sealing the hardware commands for the request and > adding the request to the software tracking. > > Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> Reviewed-by: Mika Kuoppala <mika.kuoppala@xxxxxxxxx> > --- > drivers/gpu/drm/i915/i915_gem_request.c | 28 ++++++++++++++-------------- > 1 file changed, 14 insertions(+), 14 deletions(-) > > diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c > index c60a7b774cc6..34571e1eb328 100644 > --- a/drivers/gpu/drm/i915/i915_gem_request.c > +++ b/drivers/gpu/drm/i915/i915_gem_request.c > @@ -492,6 +492,8 @@ void __i915_add_request(struct drm_i915_gem_request *request, bool flush_caches) > u32 reserved_tail; > int ret; > > + trace_i915_gem_request_add(request); > + > /* > * To ensure that this call will not fail, space for its emissions > * should already have been reserved in the ring buffer. Let the ring > @@ -515,20 +517,6 @@ void __i915_add_request(struct drm_i915_gem_request *request, bool flush_caches) > WARN(ret, "engine->emit_flush() failed: %d!\n", ret); > } > > - trace_i915_gem_request_add(request); > - > - /* Seal the request and mark it as pending execution. Note that > - * we may inspect this state, without holding any locks, during > - * hangcheck. Hence we apply the barrier to ensure that we do not > - * see a more recent value in the hws than we are tracking. > - */ > - request->emitted_jiffies = jiffies; > - request->previous_seqno = engine->last_submitted_seqno; > - engine->last_submitted_seqno = request->fence.seqno; > - i915_gem_active_set(&engine->last_request, request); > - list_add_tail(&request->link, &engine->request_list); > - list_add_tail(&request->ring_link, &ring->request_list); > - > /* Record the position of the start of the breadcrumb so that > * should we detect the updated seqno part-way through the > * GPU processing the request, we never over-estimate the > @@ -549,6 +537,18 @@ void __i915_add_request(struct drm_i915_gem_request *request, bool flush_caches) > "for adding the request (%d bytes)\n", > reserved_tail, ret); > > + /* Seal the request and mark it as pending execution. Note that > + * we may inspect this state, without holding any locks, during > + * hangcheck. Hence we apply the barrier to ensure that we do not > + * see a more recent value in the hws than we are tracking. > + */ > + request->emitted_jiffies = jiffies; > + request->previous_seqno = engine->last_submitted_seqno; > + engine->last_submitted_seqno = request->fence.seqno; > + i915_gem_active_set(&engine->last_request, request); > + list_add_tail(&request->link, &engine->request_list); > + list_add_tail(&request->ring_link, &ring->request_list); > + > i915_gem_mark_busy(engine); > > local_bh_disable(); > -- > 2.9.3 _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
