Revert "avcodec: add FF_CODEC_CAP_INIT_CLEANUP for all codecs which use ff_mpv_common_init()"

This mostly reverts commit 4b2863ff01.
Said commit removed the freeing code from ff_mpv_common_init(),
ff_mpv_common_frame_size_change() and ff_mpeg_framesize_alloc() and
instead added the FF_CODEC_CAP_INIT_CLEANUP to several codecs that use
ff_mpv_common_init(). This introduced several bugs:

a) Several decoders using ff_mpv_common_init() in their init function were
forgotten: This affected FLV, Intel H.263, RealVideo 3.0 and V4.0 as well as
VC-1/WMV3.
b) ff_mpv_common_init() is not only called from the init function of
codecs, it is also called from AVCodec.decode functions. If an error
happens after an allocation has succeeded, it can lead to memleaks;
furthermore, it is now possible for the MpegEncContext to be marked as
initialized even when ff_mpv_common_init() returns an error and this can
lead to segfaults because decoders that call ff_mpv_common_init() when
decoding a frame can mistakenly think that the MpegEncContext has been
properly initialized. This can e.g. happen with H.261 or MPEG-4.
c) Removing code for freeing from ff_mpeg_framesize_alloc() (which can't
be called from any init function) can lead to segfaults because the
check for whether it needs to allocate consists of checking whether the
first of the buffers allocated there has been allocated. This part has
already been fixed in 76cea1d2ce.
d) ff_mpv_common_frame_size_change() can also not be reached from any
AVCodec.init function; yet the changes can e.g. lead to segfaults with
decoders using ff_h263_decode_frame() upon allocation failure, because
the MpegEncContext will upon return be flagged as both initialized and
not in need of reinitialization (granted, the fact that
ff_h263_decode_frame() clears context_reinit before the context has been
reinited is a bug in itself). With the earlier version, the context
would be cleaned upon failure and it would be attempted to initialize
the context again in the next call to ff_h263_decode_frame().

While a) could be fixed by adding the missing FF_CODEC_CAP_INIT_CLEANUP,
keeping the current approach would entail adding cleanup code to several
other places because of b). Therefore ff_mpv_common_init() is again made
to clean up after itself; the changes to the wmv2 decoder and the SVQ1
encoder have not been reverted: The former fixed a memleak, the latter
allowed to remove cleanup code.

Fixes: double free
Fixes: ff_free_picture_tables.mp4
Fixes: ff_mpeg_update_thread_context.mp4
Fixes: decode_colskip.mp4
Fixes: memset.mp4

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>

libavcodec/h261dec.c

@@ -678,6 +678,6 @@ AVCodec ff_h261_decoder = {
     .close          = h261_decode_end,
     .decode         = h261_decode_frame,
     .capabilities   = AV_CODEC_CAP_DR1,
-    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_INIT_CLEANUP,
+    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE,
     .max_lowres     = 3,
 };

libavcodec/h263dec.c

@@ -771,7 +771,7 @@ AVCodec ff_h263_decoder = {
     .decode         = ff_h263_decode_frame,
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1 |
                       AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY,
-    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM | FF_CODEC_CAP_INIT_CLEANUP,
+    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .flush          = ff_mpeg_flush,
     .max_lowres     = 3,
     .pix_fmts       = ff_h263_hwaccel_pixfmt_list_420,
@@ -789,7 +789,7 @@ AVCodec ff_h263p_decoder = {
     .decode         = ff_h263_decode_frame,
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1 |
                       AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY,
-    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM | FF_CODEC_CAP_INIT_CLEANUP,
+    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .flush          = ff_mpeg_flush,
     .max_lowres     = 3,
     .pix_fmts       = ff_h263_hwaccel_pixfmt_list_420,

libavcodec/mpeg12dec.c

@@ -2880,7 +2880,8 @@ static av_cold int mpeg_decode_end(AVCodecContext *avctx)
 {
     Mpeg1Context *s = avctx->priv_data;
 
-    ff_mpv_common_end(&s->mpeg_enc_ctx);
+    if (s->mpeg_enc_ctx_allocated)
+        ff_mpv_common_end(&s->mpeg_enc_ctx);
     av_buffer_unref(&s->a53_buf_ref);
     return 0;
 }
@@ -2897,7 +2898,7 @@ AVCodec ff_mpeg1video_decoder = {
     .capabilities          = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1 |
                              AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY |
                              AV_CODEC_CAP_SLICE_THREADS,
-    .caps_internal         = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_INIT_CLEANUP |
+    .caps_internal         = FF_CODEC_CAP_INIT_THREADSAFE |
                              FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .flush                 = flush,
     .max_lowres            = 3,
@@ -2931,7 +2932,7 @@ AVCodec ff_mpeg2video_decoder = {
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1 |
                       AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY |
                       AV_CODEC_CAP_SLICE_THREADS,
-    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_INIT_CLEANUP |
+    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE |
                       FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .flush          = flush,
     .max_lowres     = 3,
@@ -2976,7 +2977,7 @@ AVCodec ff_mpegvideo_decoder = {
     .close          = mpeg_decode_end,
     .decode         = mpeg_decode_frame,
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1 | AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY | AV_CODEC_CAP_SLICE_THREADS,
-    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_INIT_CLEANUP |
+    .caps_internal  = FF_CODEC_CAP_INIT_THREADSAFE |
                       FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .flush          = flush,
     .max_lowres     = 3,

libavcodec/mpeg4videodec.c

@@ -3579,8 +3579,7 @@ AVCodec ff_mpeg4_decoder = {
                              AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY |
                              AV_CODEC_CAP_FRAME_THREADS,
     .caps_internal         = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM |
-                             FF_CODEC_CAP_ALLOCATE_PROGRESS |
-                             FF_CODEC_CAP_INIT_CLEANUP,
+                             FF_CODEC_CAP_ALLOCATE_PROGRESS,
     .flush                 = ff_mpeg_flush,
     .max_lowres            = 3,
     .pix_fmts              = ff_h263_hwaccel_pixfmt_list_420,

libavcodec/mpegvideo.c

@@ -932,17 +932,17 @@ av_cold int ff_mpv_common_init(MpegEncContext *s)
     for (i = 0; i < MAX_PICTURE_COUNT; i++) {
         s->picture[i].f = av_frame_alloc();
         if (!s->picture[i].f)
-            return AVERROR(ENOMEM);
+            goto fail_nomem;
     }
 
     if (!(s->next_picture.f    = av_frame_alloc()) ||
         !(s->last_picture.f    = av_frame_alloc()) ||
         !(s->current_picture.f = av_frame_alloc()) ||
         !(s->new_picture.f     = av_frame_alloc()))
-        return AVERROR(ENOMEM);
+        goto fail_nomem;
 
     if ((ret = init_context_frame(s)))
-        return AVERROR(ENOMEM);
+        goto fail;
 
     s->parse_context.state = -1;
 
@@ -956,10 +956,10 @@ av_cold int ff_mpv_common_init(MpegEncContext *s)
             if (i) {
                 s->thread_context[i] = av_memdup(s, sizeof(MpegEncContext));
                 if (!s->thread_context[i])
-                    return AVERROR(ENOMEM);
+                    goto fail_nomem;
             }
             if ((ret = init_duplicate_context(s->thread_context[i])) < 0)
-                return ret;
+                goto fail;
             s->thread_context[i]->start_mb_y =
                 (s->mb_height * (i) + nb_slices / 2) / nb_slices;
             s->thread_context[i]->end_mb_y   =
@@ -967,7 +967,7 @@ av_cold int ff_mpv_common_init(MpegEncContext *s)
         }
     } else {
         if ((ret = init_duplicate_context(s)) < 0)
-            return ret;
+            goto fail;
         s->start_mb_y = 0;
         s->end_mb_y   = s->mb_height;
     }
@@ -975,6 +975,11 @@ av_cold int ff_mpv_common_init(MpegEncContext *s)
 //     }
 
     return 0;
+ fail_nomem:
+    ret = AVERROR(ENOMEM);
+ fail:
+    ff_mpv_common_end(s);
+    return ret;
 }
 
 /**
@@ -1067,17 +1072,17 @@ int ff_mpv_common_frame_size_change(MpegEncContext *s)
 
     if ((s->width || s->height) &&
         (err = av_image_check_size(s->width, s->height, 0, s->avctx)) < 0)
-        return err;
+        goto fail;
 
     /* set chroma shifts */
     err = av_pix_fmt_get_chroma_sub_sample(s->avctx->pix_fmt,
                                            &s->chroma_x_shift,
                                            &s->chroma_y_shift);
     if (err < 0)
-        return err;
+        goto fail;
 
     if ((err = init_context_frame(s)))
-        return err;
+        goto fail;
 
     memset(s->thread_context, 0, sizeof(s->thread_context));
     s->thread_context[0]   = s;
@@ -1089,11 +1094,12 @@ int ff_mpv_common_frame_size_change(MpegEncContext *s)
                 if (i) {
                     s->thread_context[i] = av_memdup(s, sizeof(MpegEncContext));
                     if (!s->thread_context[i]) {
-                        return AVERROR(ENOMEM);
+                        err = AVERROR(ENOMEM);
+                        goto fail;
                     }
                 }
                 if ((err = init_duplicate_context(s->thread_context[i])) < 0)
-                    return err;
+                    goto fail;
                 s->thread_context[i]->start_mb_y =
                     (s->mb_height * (i) + nb_slices / 2) / nb_slices;
                 s->thread_context[i]->end_mb_y   =
@@ -1102,7 +1108,7 @@ int ff_mpv_common_frame_size_change(MpegEncContext *s)
         } else {
             err = init_duplicate_context(s);
             if (err < 0)
-                return err;
+                goto fail;
             s->start_mb_y = 0;
             s->end_mb_y   = s->mb_height;
         }
@@ -1110,6 +1116,9 @@ int ff_mpv_common_frame_size_change(MpegEncContext *s)
     }
 
     return 0;
+ fail:
+    ff_mpv_common_end(s);
+    return err;
 }
 
 /* init common structure for both encoder and decoder */

libavcodec/msmpeg4dec.c

@@ -870,7 +870,7 @@ AVCodec ff_msmpeg4v1_decoder = {
     .close          = ff_h263_decode_end,
     .decode         = ff_h263_decode_frame,
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1,
-    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM | FF_CODEC_CAP_INIT_CLEANUP,
+    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .max_lowres     = 3,
     .pix_fmts       = (const enum AVPixelFormat[]) {
         AV_PIX_FMT_YUV420P,
@@ -888,7 +888,7 @@ AVCodec ff_msmpeg4v2_decoder = {
     .close          = ff_h263_decode_end,
     .decode         = ff_h263_decode_frame,
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1,
-    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM | FF_CODEC_CAP_INIT_CLEANUP,
+    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .max_lowres     = 3,
     .pix_fmts       = (const enum AVPixelFormat[]) {
         AV_PIX_FMT_YUV420P,
@@ -906,7 +906,7 @@ AVCodec ff_msmpeg4v3_decoder = {
     .close          = ff_h263_decode_end,
     .decode         = ff_h263_decode_frame,
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1,
-    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM | FF_CODEC_CAP_INIT_CLEANUP,
+    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .max_lowres     = 3,
     .pix_fmts       = (const enum AVPixelFormat[]) {
         AV_PIX_FMT_YUV420P,
@@ -924,7 +924,7 @@ AVCodec ff_wmv1_decoder = {
     .close          = ff_h263_decode_end,
     .decode         = ff_h263_decode_frame,
     .capabilities   = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1,
-    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM | FF_CODEC_CAP_INIT_CLEANUP,
+    .caps_internal  = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM,
     .max_lowres     = 3,
     .pix_fmts       = (const enum AVPixelFormat[]) {
         AV_PIX_FMT_YUV420P,

libavcodec/rv10.c

@@ -687,7 +687,6 @@ AVCodec ff_rv10_decoder = {
     .close          = rv10_decode_end,
     .decode         = rv10_decode_frame,
     .capabilities   = AV_CODEC_CAP_DR1,
-    .caps_internal  = FF_CODEC_CAP_INIT_CLEANUP,
     .max_lowres     = 3,
     .pix_fmts       = (const enum AVPixelFormat[]) {
         AV_PIX_FMT_YUV420P,
@@ -705,7 +704,6 @@ AVCodec ff_rv20_decoder = {
     .close          = rv10_decode_end,
     .decode         = rv10_decode_frame,
     .capabilities   = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_DELAY,
-    .caps_internal  = FF_CODEC_CAP_INIT_CLEANUP,
     .flush          = ff_mpeg_flush,
     .max_lowres     = 3,
     .pix_fmts       = (const enum AVPixelFormat[]) {