[FFmpeg-devel] [PATCH v1 1/4] lavc/vaapi_encode_h265: Add P frame to GPB frame support for hevc_vaapi

[Fei Wang]

From: Linjie Fu <linjie.fu at intel.com>

Use GPB frames to replace regular P frames if backend driver does not
support it.

- GPB:
    Generalized P and B picture. P frames replaced by B frames with
    forward-predict only, L0 == L1. Normal B frames still have 2
    different ref_lists and allow bi-prediction

Signed-off-by: Linjie Fu <linjie.fu at intel.com>
Signed-off-by: Fei Wang <fei.w.wang at intel.com>
---
 libavcodec/vaapi_encode.c      | 33 +++++++++++++++++++++++++++++++--
 libavcodec/vaapi_encode.h      |  1 +
 libavcodec/vaapi_encode_h265.c | 15 +++++++++++++++
 3 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/libavcodec/vaapi_encode.c b/libavcodec/vaapi_encode.c
index 3bf379b1a0..95eca7c288 100644
--- a/libavcodec/vaapi_encode.c
+++ b/libavcodec/vaapi_encode.c
@@ -1845,6 +1845,30 @@ static av_cold int vaapi_encode_init_gop_structure(AVCodecContext *avctx)
         ref_l1 = attr.value >> 16 & 0xffff;
     }
 
+    ctx->p_to_gpb = 0;
+
+#if VA_CHECK_VERSION(1, 9, 0)
+    attr = (VAConfigAttrib) { VAConfigAttribPredictionDirection };
+    vas = vaGetConfigAttributes(ctx->hwctx->display,
+                                ctx->va_profile,
+                                ctx->va_entrypoint,
+                                &attr, 1);
+    if (vas != VA_STATUS_SUCCESS) {
+        av_log(avctx, AV_LOG_WARNING, "Failed to query prediction direction "
+               "attribute: %d (%s).\n", vas, vaErrorStr(vas));
+    } else if (attr.value == VA_ATTRIB_NOT_SUPPORTED) {
+        av_log(avctx, AV_LOG_VERBOSE, "Driver does not report whether "
+               "support GPB, use regular P frames.\n");
+    } else {
+        if (attr.value & VA_PREDICTION_DIRECTION_BI_NOT_EMPTY) {
+            ctx->p_to_gpb = 1;
+            av_log(avctx, AV_LOG_VERBOSE, "Use GPB B frames to replace "
+                   "regular P frames.\n");
+        } else
+            av_log(avctx, AV_LOG_VERBOSE, "Use regular P frames.\n");
+    }
+#endif
+
     if (ctx->codec->flags & FLAG_INTRA_ONLY ||
         avctx->gop_size <= 1) {
         av_log(avctx, AV_LOG_VERBOSE, "Using intra frames only.\n");
@@ -1861,8 +1885,13 @@ static av_cold int vaapi_encode_init_gop_structure(AVCodecContext *avctx)
         ctx->p_per_i  = INT_MAX;
         ctx->b_per_p  = 0;
     } else {
-        av_log(avctx, AV_LOG_VERBOSE, "Using intra, P- and B-frames "
-               "(supported references: %d / %d).\n", ref_l0, ref_l1);
+       if (ctx->p_to_gpb)
+           av_log(avctx, AV_LOG_VERBOSE, "Using intra, GPB-B-frames and "
+                  "B-frames (supported references: %d / %d).\n",
+                  ref_l0, ref_l1);
+       else
+           av_log(avctx, AV_LOG_VERBOSE, "Using intra, P- and B-frames "
+                  "(supported references: %d / %d).\n", ref_l0, ref_l1);
         ctx->gop_size = avctx->gop_size;
         ctx->p_per_i  = INT_MAX;
         ctx->b_per_p  = avctx->max_b_frames;
diff --git a/libavcodec/vaapi_encode.h b/libavcodec/vaapi_encode.h
index b41604a883..61c5615eb8 100644
--- a/libavcodec/vaapi_encode.h
+++ b/libavcodec/vaapi_encode.h
@@ -328,6 +328,7 @@ typedef struct VAAPIEncodeContext {
     int idr_counter;
     int gop_counter;
     int end_of_stream;
+    int p_to_gpb;
 
     // Whether the driver supports ROI at all.
     int             roi_allowed;
diff --git a/libavcodec/vaapi_encode_h265.c b/libavcodec/vaapi_encode_h265.c
index e1dc53dfa9..ea45893508 100644
--- a/libavcodec/vaapi_encode_h265.c
+++ b/libavcodec/vaapi_encode_h265.c
@@ -886,6 +886,7 @@ static int vaapi_encode_h265_init_slice_params(AVCodecContext *avctx,
                                                VAAPIEncodePicture *pic,
                                                VAAPIEncodeSlice *slice)
 {
+    VAAPIEncodeContext                *ctx = avctx->priv_data;
     VAAPIEncodeH265Context           *priv = avctx->priv_data;
     VAAPIEncodeH265Picture           *hpic = pic->priv_data;
     const H265RawSPS                  *sps = &priv->raw_sps;
@@ -908,6 +909,9 @@ static int vaapi_encode_h265_init_slice_params(AVCodecContext *avctx,
 
     sh->slice_type = hpic->slice_type;
 
+    if (sh->slice_type == HEVC_SLICE_P && ctx->p_to_gpb)
+        sh->slice_type = HEVC_SLICE_B;
+
     sh->slice_pic_order_cnt_lsb = hpic->pic_order_cnt &
         (1 << (sps->log2_max_pic_order_cnt_lsb_minus4 + 4)) - 1;
 
@@ -1066,6 +1070,9 @@ static int vaapi_encode_h265_init_slice_params(AVCodecContext *avctx,
         av_assert0(pic->type == PICTURE_TYPE_P ||
                    pic->type == PICTURE_TYPE_B);
         vslice->ref_pic_list0[0] = vpic->reference_frames[0];
+        if (ctx->p_to_gpb && pic->type == PICTURE_TYPE_P)
+            // Reference for GPB B-frame, L0 == L1
+            vslice->ref_pic_list1[0] = vpic->reference_frames[0];
     }
     if (pic->nb_refs >= 2) {
         // Forward reference for B-frame.
@@ -1073,6 +1080,14 @@ static int vaapi_encode_h265_init_slice_params(AVCodecContext *avctx,
         vslice->ref_pic_list1[0] = vpic->reference_frames[1];
     }
 
+    if (pic->type == PICTURE_TYPE_P && ctx->p_to_gpb) {
+        vslice->slice_type = HEVC_SLICE_B;
+        for (i = 0; i < FF_ARRAY_ELEMS(vslice->ref_pic_list0); i++) {
+            vslice->ref_pic_list1[i].picture_id = vslice->ref_pic_list0[i].picture_id;
+            vslice->ref_pic_list1[i].flags      = vslice->ref_pic_list0[i].flags;
+        }
+    }
+
     return 0;
 }
 
-- 
2.25.1