h264: fix frame reordering code.

Fixes fate-h264-conformance-{mr2_tandberg_e,mr3_tandberg_b} without
requiring -strict 1.

3 files changed, 52 insertions, 22 deletions

diff --git a/libavcodec/h264.c b/libavcodec/h264.c
index 96062b7806..acd7179cc0 100644
--- a/libavcodec/h264.c
+++ b/libavcodec/h264.c
@@ -1348,6 +1348,7 @@ static void decode_postinit(H264Context *h, int setup_finished){
     Picture *out = s->current_picture_ptr;
     Picture *cur = s->current_picture_ptr;
     int i, pics, out_of_order, out_idx;
+    int invalid = 0, cnt = 0;
 
     s->current_picture_ptr->f.qscale_type = FF_QSCALE_TYPE_H264;
     s->current_picture_ptr->f.pict_type   = s->pict_type;
@@ -1451,31 +1452,54 @@ static void decode_postinit(H264Context *h, int setup_finished){
     if (cur->f.reference == 0)
         cur->f.reference = DELAYED_PIC_REF;
 
+    /* Frame reordering. This code takes pictures from coding order and sorts
+     * them by their incremental POC value into display order. It supports POC
+     * gaps, MMCO reset codes and random resets.
+     * A "display group" can start either with a IDR frame (f.key_frame = 1),
+     * and/or can be closed down with a MMCO reset code. In sequences where
+     * there is no delay, we can't detect that (since the frame was already
+     * output to the user), so we also set h->mmco_reset to detect the MMCO
+     * reset code.
+     * FIXME: if we detect insufficient delays (as per s->avctx->has_b_frames),
+     * we increase the delay between input and output. All frames affected by
+     * the lag (e.g. those that should have been output before another frame
+     * that we already returned to the user) will be dropped. This is a bug
+     * that we will fix later. */
+    for (i = 0; i < MAX_DELAYED_PIC_COUNT; i++) {
+        cnt     += out->poc < h->last_pocs[i];
+        invalid += out->poc == INT_MIN;
+    }
+    if (!h->mmco_reset && !cur->f.key_frame && cnt + invalid == MAX_DELAYED_PIC_COUNT && cnt > 0) {
+        h->mmco_reset = 2;
+        if (pics > 1)
+            h->delayed_pic[pics - 2]->mmco_reset = 2;
+    }
+    if (h->mmco_reset || cur->f.key_frame) {
+        for (i = 0; i < MAX_DELAYED_PIC_COUNT; i++)
+            h->last_pocs[i] = INT_MIN;
+        cnt     = 0;
+        invalid = MAX_DELAYED_PIC_COUNT;
+    }
     out = h->delayed_pic[0];
     out_idx = 0;
-    for (i = 1; h->delayed_pic[i] && !h->delayed_pic[i]->f.key_frame && !h->delayed_pic[i]->mmco_reset; i++)
+    for (i = 1; i < MAX_DELAYED_PIC_COUNT && h->delayed_pic[i] &&
+         !h->delayed_pic[i-1]->mmco_reset && !h->delayed_pic[i]->f.key_frame; i++)
+    {
         if(h->delayed_pic[i]->poc < out->poc){
             out = h->delayed_pic[i];
             out_idx = i;
         }
-    if (s->avctx->has_b_frames == 0 && (h->delayed_pic[0]->f.key_frame || h->delayed_pic[0]->mmco_reset))
-        h->next_outputed_poc= INT_MIN;
-    out_of_order = out->poc < h->next_outputed_poc;
+    }
+    if (s->avctx->has_b_frames == 0 && (h->delayed_pic[0]->f.key_frame || h->mmco_reset))
+        h->next_outputed_poc = INT_MIN;
+    out_of_order = !out->f.key_frame && !h->mmco_reset && (out->poc < h->next_outputed_poc);
 
     if(h->sps.bitstream_restriction_flag && s->avctx->has_b_frames >= h->sps.num_reorder_frames)
         { }
     else if (out_of_order && pics-1 == s->avctx->has_b_frames &&
              s->avctx->has_b_frames < MAX_DELAYED_PIC_COUNT) {
-        int cnt = 0, invalid = 0;
-        for (i = 0; i < MAX_DELAYED_PIC_COUNT; i++) {
-            cnt += out->poc < h->last_pocs[i];
-            invalid += h->last_pocs[i] == INT_MIN;
-        }
         if (invalid + cnt < MAX_DELAYED_PIC_COUNT) {
             s->avctx->has_b_frames = FFMAX(s->avctx->has_b_frames, cnt);
-        } else if (cnt) {
-            for (i = 0; i < MAX_DELAYED_PIC_COUNT; i++)
-                h->last_pocs[i] = INT_MIN;
         }
         s->low_delay = 0;
     } else if (s->low_delay &&
@@ -1485,7 +1509,7 @@ static void decode_postinit(H264Context *h, int setup_finished){
         s->avctx->has_b_frames++;
     }
 
-    if(out_of_order || pics > s->avctx->has_b_frames){
+    if(pics > s->avctx->has_b_frames){
         out->f.reference &= ~DELAYED_PIC_REF;
         out->owner2 = s; // for frame threading, the owner must be the second field's thread
                          // or else the first thread can release the picture and reuse it unsafely
@@ -1493,13 +1517,20 @@ static void decode_postinit(H264Context *h, int setup_finished){
             h->delayed_pic[i] = h->delayed_pic[i+1];
     }
     memmove(h->last_pocs, &h->last_pocs[1], sizeof(*h->last_pocs) * (MAX_DELAYED_PIC_COUNT - 1));
-    h->last_pocs[MAX_DELAYED_PIC_COUNT - 1] = out->poc;
+    h->last_pocs[MAX_DELAYED_PIC_COUNT - 1] = cur->poc;
     if(!out_of_order && pics > s->avctx->has_b_frames){
         h->next_output_pic = out;
-        if (out_idx == 0 && h->delayed_pic[0] && (h->delayed_pic[0]->f.key_frame || h->delayed_pic[0]->mmco_reset)) {
-            h->next_outputed_poc = INT_MIN;
-        } else
+        if (out->mmco_reset) {
+            if (out_idx > 0) {
+                h->next_outputed_poc = out->poc;
+                h->delayed_pic[out_idx - 1]->mmco_reset = out->mmco_reset;
+            } else {
+                h->next_outputed_poc = INT_MIN;
+            }
+        } else {
             h->next_outputed_poc = out->poc;
+        }
+        h->mmco_reset = 0;
     }else{
         av_log(s->avctx, AV_LOG_DEBUG, "no picture\n");
     }
@@ -2353,6 +2384,8 @@ static void flush_dpb(AVCodecContext *avctx){
             h->delayed_pic[i]->f.reference = 0;
         h->delayed_pic[i]= NULL;
     }
+    for (i = 0; i < MAX_DELAYED_PIC_COUNT; i++)
+        h->last_pocs[i] = INT_MIN;
     h->outputed_poc=h->next_outputed_poc= INT_MIN;
     h->prev_interlaced_frame = 1;
     idr(h);
diff --git a/libavcodec/h264.h b/libavcodec/h264.h
index caea7ba7eb..5280e5155a 100644
--- a/libavcodec/h264.h
+++ b/libavcodec/h264.h
@@ -498,6 +498,7 @@ typedef struct H264Context{
      */
     MMCO mmco[MAX_MMCO_COUNT];
     int mmco_index;
+    int mmco_reset;
 
     int long_ref_count;  ///< number of actual long term references
     int short_ref_count; ///< number of actual short term references
diff --git a/libavcodec/h264_refs.c b/libavcodec/h264_refs.c
index 370b5c312d..273c52b475 100644
--- a/libavcodec/h264_refs.c
+++ b/libavcodec/h264_refs.c
@@ -582,13 +582,9 @@ int ff_h264_execute_ref_pic_marking(H264Context *h, MMCO *mmco, int mmco_count){
             for(j = 0; j < 16; j++) {
                 remove_long(h, j, 0);
             }
-            s->current_picture_ptr->poc=
-            s->current_picture_ptr->field_poc[0]=
-            s->current_picture_ptr->field_poc[1]=
-            h->poc_lsb=
-            h->poc_msb=
             h->frame_num=
             s->current_picture_ptr->frame_num= 0;
+            h->mmco_reset = 1;
             s->current_picture_ptr->mmco_reset=1;
             break;
         default: assert(0);