vaapi: add vaapi_cavs support

see intel/libva#738

[Moore Threads](https://www.mthreads.com) (short for Mthreads) is a
Chinese GPU manufacturer. All our products, like MTTS70/MTTS80/.. ,
support AVS/AVS+ HW decoding at max 2k resolution.

Signed-off-by: jianfeng.zheng <[email protected]>

configure

@@ -2463,6 +2463,7 @@ HAVE_LIST="
     xmllint
     zlib_gzip
     openvino2
+    va_profile_avs
 "
 
 # options emitted with CONFIG_ prefix but not available on the command line
@@ -3202,6 +3203,7 @@ wmv3_dxva2_hwaccel_select="vc1_dxva2_hwaccel"
 wmv3_nvdec_hwaccel_select="vc1_nvdec_hwaccel"
 wmv3_vaapi_hwaccel_select="vc1_vaapi_hwaccel"
 wmv3_vdpau_hwaccel_select="vc1_vdpau_hwaccel"
+cavs_vaapi_hwaccel_deps="vaapi va_profile_avs VAPictureParameterBufferAVS"
 
 # hardware-accelerated codecs
 mediafoundation_deps="mftransform_h MFCreateAlignedMemoryBuffer"
@@ -7175,6 +7177,18 @@ if enabled vaapi; then
     check_type "va/va.h va/va_enc_vp8.h"  "VAEncPictureParameterBufferVP8"
     check_type "va/va.h va/va_enc_vp9.h"  "VAEncPictureParameterBufferVP9"
     check_type "va/va.h va/va_enc_av1.h"  "VAEncPictureParameterBufferAV1"
+
+    #
+    # Using 'VA_CHECK_VERSION' in source codes make things easy. But we have to wait
+    # until newly added VAProfile being distributed by VAAPI released version.
+    #
+    # Before or after that, we can use auto-detection to keep version compatibility.
+    # It always works.
+    #
+    disable va_profile_avs &&
+        test_code cc va/va.h "VAProfile p1 = VAProfileAVSJizhun, p2 = VAProfileAVSGuangdian;" &&
+        enable va_profile_avs
+    enabled va_profile_avs && check_type "va/va.h va/va_dec_avs.h" "VAPictureParameterBufferAVS"
 fi
 
 if enabled_all opencl libdrm ; then

libavcodec/Makefile

@@ -1055,6 +1055,7 @@ OBJS-$(CONFIG_VP9_VAAPI_HWACCEL)          += vaapi_vp9.o
 OBJS-$(CONFIG_VP9_VDPAU_HWACCEL)          += vdpau_vp9.o
 OBJS-$(CONFIG_VP9_VIDEOTOOLBOX_HWACCEL)   += videotoolbox_vp9.o
 OBJS-$(CONFIG_VP8_QSV_HWACCEL)            += qsvdec.o
+OBJS-$(CONFIG_CAVS_VAAPI_HWACCEL)         += vaapi_cavs.o
 
 # Objects duplicated from other libraries for shared builds
 SHLIBOBJS                              += log2_tab.o reverse.o

libavcodec/cavs.c

@@ -810,6 +810,14 @@ av_cold int ff_cavs_init(AVCodecContext *avctx)
     if (!h->cur.f || !h->DPB[0].f || !h->DPB[1].f)
         return AVERROR(ENOMEM);
 
+    h->out[0].f = av_frame_alloc();
+    h->out[1].f = av_frame_alloc();
+    h->out[2].f = av_frame_alloc();
+    if (!h->out[0].f || !h->out[1].f || !h->out[2].f) {
+        ff_cavs_end(avctx);
+        return AVERROR(ENOMEM);
+    }
+
     h->luma_scan[0]                     = 0;
     h->luma_scan[1]                     = 8;
     h->intra_pred_l[INTRA_L_VERT]       = intra_pred_vert;
@@ -840,6 +848,10 @@ av_cold int ff_cavs_end(AVCodecContext *avctx)
     av_frame_free(&h->DPB[0].f);
     av_frame_free(&h->DPB[1].f);
 
+    av_frame_free(&h->out[0].f);
+    av_frame_free(&h->out[1].f);
+    av_frame_free(&h->out[2].f);
+
     av_freep(&h->top_qp);
     av_freep(&h->top_mv[0]);
     av_freep(&h->top_mv[1]);

libavcodec/cavs.h

@@ -39,8 +39,10 @@
 #define EXT_START_CODE          0x000001b5
 #define USER_START_CODE         0x000001b2
 #define CAVS_START_CODE         0x000001b0
+#define VIDEO_SEQ_END_CODE      0x000001b1
 #define PIC_I_START_CODE        0x000001b3
 #define PIC_PB_START_CODE       0x000001b6
+#define VIDEO_EDIT_CODE         0x000001b7
 
 #define A_AVAIL                          1
 #define B_AVAIL                          2
@@ -164,30 +166,62 @@ struct dec_2dvlc {
 typedef struct AVSFrame {
     AVFrame *f;
     int poc;
+    int outputed;
+
+    AVBufferRef   *hwaccel_priv_buf;
+    void          *hwaccel_picture_private;
 } AVSFrame;
 
 typedef struct AVSContext {
     AVCodecContext *avctx;
+    int got_pix_fmt;
     BlockDSPContext bdsp;
     H264ChromaContext h264chroma;
     VideoDSPContext vdsp;
     CAVSDSPContext  cdsp;
     GetBitContext gb;
     AVSFrame cur;     ///< currently decoded frame
     AVSFrame DPB[2];  ///< reference frames
+    AVSFrame out[3];  ///< output queue, size 2 maybe enough
     int dist[2];     ///< temporal distances from current frame to ref frames
     int low_delay;
     int profile, level;
     int aspect_ratio;
     int mb_width, mb_height;
     int width, height;
     int stream_revision; ///<0 for samples from 2006, 1 for rm52j encoder
-    int progressive;
+    int progressive_seq;
+    int progressive_frame;
     int pic_structure;
+    int no_forward_ref_flag;
+    int pb_field_enhanced_flag;   ///< only used in GUANGDIAN
     int skip_mode_flag; ///< select between skip_count or one skip_flag per MB
     int loop_filter_disable;
     int alpha_offset, beta_offset;
     int ref_flag;
+
+    /** \defgroup guangdian profile
+     * @{
+     */
+    int aec_flag;
+    int weight_quant_flag;
+    int chroma_quant_param_delta_cb;
+    int chroma_quant_param_delta_cr;
+    uint8_t wqm_8x8[64];
+    /**@}*/
+
+    /** \defgroup slice weighting
+     * FFmpeg don't support slice weighting natively, but maybe needed for HWaccel.
+     * @{
+     */
+    uint32_t slice_weight_pred_flag : 1;
+    uint32_t mb_weight_pred_flag    : 1;
+    uint8_t luma_scale[4];
+    int8_t luma_shift[4];
+    uint8_t chroma_scale[4];
+    int8_t chroma_shift[4];
+    /**@}*/
+
     int mbx, mby, mbidx; ///< macroblock coordinates
     int flags;         ///< availability flags of neighbouring macroblocks
     int stc;           ///< last start code

libavcodec/cavs_parser.c

@@ -65,6 +65,22 @@ static int cavs_find_frame_end(ParseContext *pc, const uint8_t *buf,
                 pc->state=-1;
                 return i-3;
             }
+            if((state&0xFFFFFF00) == 0x100){
+                if(state != EXT_START_CODE && state != USER_START_CODE){
+                    state = state >> 8;
+                    break;
+                }
+            }
+        }
+        for(; i<buf_size; i++){
+            state= (state<<8) | buf[i];
+            if((state&0xFFFFFF00) == 0x100){
+                if(state > SLICE_MAX_START_CODE){
+                    pc->frame_start_found=0;
+                    pc->state=-1;
+                    return i-3;
+                }
+            }
         }
     }
     pc->frame_start_found= pic_found;