[Mesa-dev] [PATCH 1/2] st/va: force to submit two consecutive single jobs

[boyuan.zhang at amd.com]

From: Boyuan Zhang <boyuan.zhang at amd.com>

The gop_size in rate control is the budget window for internal rate
control calculation, and shouldn't always equal to idr period. Define
a coefficient to let budget window contains a number of idr period for
proper rate control calculation. Adjust the number of i/p frame remaining
accordingly.

Fixes: https://bugs.freedesktop.org/show_bug.cgi?id=98005

Signed-off-by: Boyuan Zhang <boyuan.zhang at amd.com>
---
 src/gallium/state_trackers/va/picture.c    | 24 +++++++++++++++++++-----
 src/gallium/state_trackers/va/surface.c    | 10 ++++++++--
 src/gallium/state_trackers/va/va_private.h |  2 ++
 3 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/src/gallium/state_trackers/va/picture.c b/src/gallium/state_trackers/va/picture.c
index a8102a4..592cdef 100644
--- a/src/gallium/state_trackers/va/picture.c
+++ b/src/gallium/state_trackers/va/picture.c
@@ -413,7 +413,6 @@ handleVAEncPictureParameterBufferType(vlVaDriver *drv, vlVaContext *context, vlV
    context->desc.h264enc.quant_i_frames = h264->pic_init_qp;
    context->desc.h264enc.quant_b_frames = h264->pic_init_qp;
    context->desc.h264enc.quant_p_frames = h264->pic_init_qp;
-   context->desc.h264enc.frame_num_cnt++;
    context->desc.h264enc.gop_cnt++;
    if (context->desc.h264enc.gop_cnt == context->desc.h264enc.gop_size)
       context->desc.h264enc.gop_cnt = 0;
@@ -569,18 +568,33 @@ vlVaEndPicture(VADriverContextP ctx, VAContextID context_id)
    if (context->decoder->entrypoint == PIPE_VIDEO_ENTRYPOINT_ENCODE) {
       coded_buf = context->coded_buf;
       getEncParamPreset(context);
+      context->desc.h264enc.frame_num_cnt++;
       context->decoder->begin_frame(context->decoder, context->target, &context->desc.base);
       context->decoder->encode_bitstream(context->decoder, context->target,
                                          coded_buf->derived_surface.resource, &feedback);
-      surf->frame_num_cnt = context->desc.h264enc.frame_num_cnt;
       surf->feedback = feedback;
       surf->coded_buf = coded_buf;
    }
 
    context->decoder->end_frame(context->decoder, context->target, &context->desc.base);
-   if (context->decoder->entrypoint == PIPE_VIDEO_ENTRYPOINT_ENCODE &&
-       context->desc.h264enc.p_remain == 1)
-      context->decoder->flush(context->decoder);
+   if (context->decoder->entrypoint == PIPE_VIDEO_ENTRYPOINT_ENCODE) {
+      surf->frame_num_cnt = context->desc.h264enc.frame_num_cnt;
+      surf->force_flushed = false;
+      if (context->first_single_submitted) {
+         context->decoder->flush(context->decoder);
+         context->first_single_submitted = false;
+         surf->force_flushed = true;
+      }
+      if (context->desc.h264enc.p_remain == 1) {
+         if ((context->desc.h264enc.frame_num_cnt % 2) != 0) {
+            context->decoder->flush(context->decoder);
+            context->first_single_submitted = true;
+         }
+         else
+            context->first_single_submitted = false;
+         surf->force_flushed = true;
+      }
+   }
    pipe_mutex_unlock(drv->mutex);
    return VA_STATUS_SUCCESS;
 }
diff --git a/src/gallium/state_trackers/va/surface.c b/src/gallium/state_trackers/va/surface.c
index f8513d9..a7f3c35 100644
--- a/src/gallium/state_trackers/va/surface.c
+++ b/src/gallium/state_trackers/va/surface.c
@@ -125,12 +125,18 @@ vlVaSyncSurface(VADriverContextP ctx, VASurfaceID render_target)
 
    if (context->decoder->entrypoint == PIPE_VIDEO_ENTRYPOINT_ENCODE) {
       int frame_diff;
-      if (context->desc.h264enc.frame_num_cnt > surf->frame_num_cnt)
+      if (context->desc.h264enc.frame_num_cnt >= surf->frame_num_cnt)
          frame_diff = context->desc.h264enc.frame_num_cnt - surf->frame_num_cnt;
       else
          frame_diff = 0xFFFFFFFF - surf->frame_num_cnt + 1 + context->desc.h264enc.frame_num_cnt;
-      if (frame_diff < 2)
+      if ((frame_diff == 0) &&
+          (surf->force_flushed == false) &&
+          (context->desc.h264enc.frame_num_cnt % 2 != 0)) {
          context->decoder->flush(context->decoder);
+         if (context->desc.h264enc.rate_ctrl.rate_ctrl_method !=
+            PIPE_H264_ENC_RATE_CONTROL_METHOD_DISABLE)
+            context->first_single_submitted = true;
+      }
       context->decoder->get_feedback(context->decoder, surf->feedback, &(surf->coded_buf->coded_size));
       surf->feedback = NULL;
    }
diff --git a/src/gallium/state_trackers/va/va_private.h b/src/gallium/state_trackers/va/va_private.h
index c9a6a41..9e3ba03 100644
--- a/src/gallium/state_trackers/va/va_private.h
+++ b/src/gallium/state_trackers/va/va_private.h
@@ -244,6 +244,7 @@ typedef struct {
    struct vl_deint_filter *deint;
    struct vlVaBuffer *coded_buf;
    int target_id;
+   bool first_single_submitted;
 } vlVaContext;
 
 typedef struct {
@@ -274,6 +275,7 @@ typedef struct {
    vlVaBuffer *coded_buf;
    void *feedback;
    unsigned int frame_num_cnt;
+   bool force_flushed;
 } vlVaSurface;
 
 // Public functions:
-- 
2.7.4