avcodec/hevcdec: Add stat_coeffs to HEVCABACState

The HEVC decoder has both HEVCContext and HEVCLocalContext
structures. The latter is supposed to be the structure
containing the per-slicethread state.

Yet that is not how it is handled in practice: Each HEVCLocalContext
has a unique HEVCContext allocated for it and each of these
coincides with the main HEVCContext except in exactly one field:
The corresponding HEVCLocalContext.
This makes it possible to pass the HEVCContext everywhere where
logically a HEVCLocalContext should be used.

This led to confusion in the first version of what eventually became
commit c8bc0f66a875bc3708d8dc11b757f2198606ffd7:
Before said commit, the initialization of the Rice parameter derivation
state was incorrect; the fix for single-threaded as well as
frame-threaded decoding was to add backup stats to HEVCContext
that are used when the cabac state is updated*, see
https://ffmpeg.org/pipermail/ffmpeg-devel/2020-August/268861.html
Yet due to what has been said above, this does not work for
slice-threading, because the each HEVCLocalContext has its own
HEVCContext, so the Rice parameter state would not be transferred
between threads.

This is fixed in c8bc0f66a875bc3708d8dc11b757f2198606ffd7
by a hack: It rederives what the previous thread was and accesses
the corresponding HEVCContext.

Fix this by treating the Rice parameter state the same way
the ordinary CABAC parameters are shared between threads:
Make them part of the same struct that is shared between
slice threads. This does not cause races, because
the parts of the code that access these Rice parameters
are a subset of the parts of code that access the CABAC parameters.

*: And if the persistent_rice_adaptation_enabled_flag is set.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>

3 files changed, 20 insertions, 17 deletions

diff --git a/libavcodec/hevc_cabac.c b/libavcodec/hevc_cabac.c
index a194f8a02a..985c97ef2a 100644
--- a/libavcodec/hevc_cabac.c
+++ b/libavcodec/hevc_cabac.c
@@ -453,19 +453,18 @@ void ff_hevc_save_states(HEVCContext *s, int ctb_addr_ts)
         (ctb_addr_ts % s->ps.sps->ctb_width == 2 ||
          (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);
+        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);
+            memcpy(s->cabac->stat_coeff, s->HEVClc->stat_coeff, HEVC_STAT_COEFFS);
         }
     }
 }
 
-static void load_states(HEVCContext *s, int thread)
+static void load_states(HEVCContext *s)
 {
-    memcpy(s->HEVClc->cabac_state, s->cabac_state, HEVC_CONTEXTS);
+    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);
+        memcpy(s->HEVClc->stat_coeff, s->cabac->stat_coeff, HEVC_STAT_COEFFS);
     }
 }
 
@@ -508,7 +507,7 @@ 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 thread)
+int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts)
 {
     if (ctb_addr_ts == s->ps.pps->ctb_addr_rs_to_ts[s->sh.slice_ctb_addr_rs]) {
         int ret = cabac_init_decoder(s);
@@ -525,7 +524,7 @@ int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts, int thread)
                 if (s->ps.sps->ctb_width == 1)
                     cabac_init_state(s);
                 else if (s->sh.dependent_slice_segment_flag == 1)
-                    load_states(s, thread);
+                    load_states(s);
             }
         }
     } else {
@@ -556,7 +555,7 @@ int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts, int thread)
                 if (s->ps.sps->ctb_width == 1)
                     cabac_init_state(s);
                 else
-                    load_states(s, thread);
+                    load_states(s);
             }
         }
     }
diff --git a/libavcodec/hevcdec.c b/libavcodec/hevcdec.c
index b0212a10a5..de1688cd2e 100644
--- a/libavcodec/hevcdec.c
+++ b/libavcodec/hevcdec.c
@@ -2502,7 +2502,7 @@ 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, 0);
+        ret = ff_hevc_cabac_init(s, ctb_addr_ts);
         if (ret < 0) {
             s->tab_slice_address[ctb_addr_rs] = -1;
             return ret;
@@ -2580,7 +2580,7 @@ static int hls_decode_entry_wpp(AVCodecContext *avctxt, void *input_ctb_row, int
             return 0;
         }
 
-        ret = ff_hevc_cabac_init(s, ctb_addr_ts, thread);
+        ret = ff_hevc_cabac_init(s, ctb_addr_ts);
         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);
@@ -3598,7 +3598,7 @@ static av_cold int hevc_decode_free(AVCodecContext *avctx)
 
     av_freep(&s->md5_ctx);
 
-    av_freep(&s->cabac_state);
+    av_freep(&s->cabac);
 
     for (i = 0; i < 3; i++) {
         av_freep(&s->sao_pixel_buffer_h[i]);
@@ -3652,8 +3652,8 @@ static av_cold int hevc_init_context(AVCodecContext *avctx)
     s->HEVClcList[0] = s->HEVClc;
     s->sList[0] = s;
 
-    s->cabac_state = av_malloc(HEVC_CONTEXTS);
-    if (!s->cabac_state)
+    s->cabac = av_malloc(sizeof(*s->cabac));
+    if (!s->cabac)
         return AVERROR(ENOMEM);
 
     s->output_frame = av_frame_alloc();
diff --git a/libavcodec/hevcdec.h b/libavcodec/hevcdec.h
index e2dba54f26..b97b7d1354 100644
--- a/libavcodec/hevcdec.h
+++ b/libavcodec/hevcdec.h
@@ -226,6 +226,11 @@ enum ScanType {
     SCAN_VERT,
 };
 
+typedef struct HEVCCABACState {
+    uint8_t state[HEVC_CONTEXTS];
+    uint8_t stat_coeff[HEVC_STAT_COEFFS];
+} HEVCCABACState;
+
 typedef struct LongTermRPS {
     int     poc[32];
     uint8_t poc_msb_present[32];
@@ -482,8 +487,7 @@ typedef struct HEVCContext {
     int                 width;
     int                 height;
 
-    uint8_t *cabac_state;
-    uint8_t stat_coeff[HEVC_STAT_COEFFS];
+    HEVCCABACState *cabac;
 
     /** 1 if the independent slice segment header was successfully parsed */
     uint8_t slice_initialized;
@@ -601,7 +605,7 @@ 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 thread);
+int ff_hevc_cabac_init(HEVCContext *s, int ctb_addr_ts);
 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);