avcodec/hevcdec: fix stat_coeff save/load for persistent_rice_adaptation_enabled_flag

It's required by the 9.3.1 TableStatCoeff* section.

Following clips have this feature:
WPP_HIGH_TP_444_8BIT_RExt_Apple_2.bit
Bitdepth_A_RExt_Sony_1.bin
Bitdepth_B_RExt_Sony_1.bin
EXTPREC_HIGHTHROUGHPUT_444_16_INTRA_10BIT_RExt_Sony_1.bit
EXTPREC_HIGHTHROUGHPUT_444_16_INTRA_12BIT_RExt_Sony_1.bit
EXTPREC_HIGHTHROUGHPUT_444_16_INTRA_8BIT_RExt_Sony_1.bit
EXTPREC_MAIN_444_16_INTRA_10BIT_RExt_Sony_1.bit
EXTPREC_MAIN_444_16_INTRA_12BIT_RExt_Sony_1.bit
EXTPREC_MAIN_444_16_INTRA_8BIT_RExt_Sony_1.bit
WPP_AND_TILE_10Bit422Test_HIGH_TP_444_10BIT_RExt_Apple_2.bit
WPP_AND_TILE_AND_CABAC_BYPASS_ALIGN_0_HIGH_TP_444_14BIT_RExt_Apple_2.bit
WPP_AND_TILE_AND_CABAC_BYPASS_ALIGN_1_HIGH_TP_444_14BIT_RExt_Apple_2.bit
WPP_AND_TILE_HIGH_TP_444_8BIT_RExt_Apple_2.bit

you can download them from:
https://www.itu.int/wftp3/av-arch/jctvc-site/bitstream_exchange/draft_conformance/RExt/

Signed-off-by: Xu Guangxin <oddstone@gmail.com>
Signed-off-by: Linjie Fu <linjie.justin.fu@gmail.com>

libavcodec/hevc_cabac.c

@@ -454,12 +454,19 @@ void ff_hevc_save_states(HEVCContext *s, int ctb_addr_ts)
          (s->ps.sps->ctb_width == 2 &&
           ctb_addr_ts % s->ps.sps->ctb_width == 0))) {
         memcpy(s->cabac_state, s->HEVClc->cabac_state, HEVC_CONTEXTS);
+        if (s->ps.sps->persistent_rice_adaptation_enabled_flag) {
+            memcpy(s->stat_coeff, s->HEVClc->stat_coeff, HEVC_STAT_COEFFS);
+        }
     }
 }
 
-static void load_states(HEVCContext *s)
+static void load_states(HEVCContext *s, int thread)
 {
     memcpy(s->HEVClc->cabac_state, s->cabac_state, HEVC_CONTEXTS);
+    if (s->ps.sps->persistent_rice_adaptation_enabled_flag) {
+        const HEVCContext *prev = s->sList[(thread + s->threads_number - 1) % s->threads_number];
+        memcpy(s->HEVClc->stat_coeff, prev->stat_coeff, HEVC_STAT_COEFFS);
+    }
 }
 
 static int cabac_reinit(HEVCLocalContext *lc)
@@ -501,7 +508,7 @@ static void cabac_init_state(HEVCContext *s)
         s->HEVClc->stat_coeff[i] = 0;
 }
 
-int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts)
+int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts, int thread)
 {
     if (ctb_addr_ts == s->ps.pps->ctb_addr_rs_to_ts[s->sh.slice_ctb_addr_rs]) {
         int ret = cabac_init_decoder(s);
@@ -518,7 +525,7 @@ int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts)
                 if (s->ps.sps->ctb_width == 1)
                     cabac_init_state(s);
                 else if (s->sh.dependent_slice_segment_flag == 1)
-                    load_states(s);
+                    load_states(s, thread);
             }
         }
     } else {
@@ -549,7 +556,7 @@ int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts)
                 if (s->ps.sps->ctb_width == 1)
                     cabac_init_state(s);
                 else
-                    load_states(s);
+                    load_states(s, thread);
             }
         }
     }

libavcodec/hevcdec.c

@@ -2473,7 +2473,7 @@ static int hls_decode_entry(AVCodecContext *avctxt, void *isFilterThread)
         y_ctb = (ctb_addr_rs / ((s->ps.sps->width + ctb_size - 1) >> s->ps.sps->log2_ctb_size)) << s->ps.sps->log2_ctb_size;
         hls_decode_neighbour(s, x_ctb, y_ctb, ctb_addr_ts);
 
-        ret = ff_hevc_cabac_init(s, ctb_addr_ts);
+        ret = ff_hevc_cabac_init(s, ctb_addr_ts, 0);
         if (ret < 0) {
             s->tab_slice_address[ctb_addr_rs] = -1;
             return ret;
@@ -2551,7 +2551,7 @@ static int hls_decode_entry_wpp(AVCodecContext *avctxt, void *input_ctb_row, int
             return 0;
         }
 
-        ret = ff_hevc_cabac_init(s, ctb_addr_ts);
+        ret = ff_hevc_cabac_init(s, ctb_addr_ts, thread);
         if (ret < 0)
             goto error;
         hls_sao_param(s, x_ctb >> s->ps.sps->log2_ctb_size, y_ctb >> s->ps.sps->log2_ctb_size);

libavcodec/hevcdec.h

@@ -53,6 +53,7 @@
 #define DEFAULT_INTRA_TC_OFFSET 2
 
 #define HEVC_CONTEXTS 199
+#define HEVC_STAT_COEFFS 4
 
 #define MRG_MAX_NUM_CANDS     5
 
@@ -424,7 +425,7 @@ typedef struct HEVCFrame {
 typedef struct HEVCLocalContext {
     uint8_t cabac_state[HEVC_CONTEXTS];
 
-    uint8_t stat_coeff[4];
+    uint8_t stat_coeff[HEVC_STAT_COEFFS];
 
     uint8_t first_qp_group;
 
@@ -480,6 +481,7 @@ typedef struct HEVCContext {
     int                 height;
 
     uint8_t *cabac_state;
+    uint8_t stat_coeff[HEVC_STAT_COEFFS];
 
     /** 1 if the independent slice segment header was successfully parsed */
     uint8_t slice_initialized;
@@ -594,7 +596,7 @@ int ff_hevc_frame_rps(HEVCContext *s);
 int ff_hevc_slice_rpl(HEVCContext *s);
 
 void ff_hevc_save_states(HEVCContext *s, int ctb_addr_ts);
-int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts);
+int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts, int thread);
 int ff_hevc_sao_merge_flag_decode(HEVCContext *s);
 int ff_hevc_sao_type_idx_decode(HEVCContext *s);
 int ff_hevc_sao_band_position_decode(HEVCContext *s);