aac_latm: Allow unaligned AudioSpecificConfig

Fixes ticket 4730

libavcodec/aacdec.c

@@ -284,9 +284,10 @@ static int latm_decode_audio_specific_config(struct LATMContext *latmctx,
     AACContext *ac        = &latmctx->aac_ctx;
     AVCodecContext *avctx = ac->avctx;
     MPEG4AudioConfig m4ac = { 0 };
+    GetBitContext gbc;
     int config_start_bit  = get_bits_count(gb);
     int sync_extension    = 0;
-    int bits_consumed, esize;
+    int bits_consumed, esize, i;
 
     if (asclen) {
         sync_extension = 1;
@@ -294,19 +295,19 @@ static int latm_decode_audio_specific_config(struct LATMContext *latmctx,
     } else
         asclen         = get_bits_left(gb);
 
-    if (config_start_bit % 8) {
-        avpriv_request_sample(latmctx->aac_ctx.avctx,
-                              "Non-byte-aligned audio-specific config");
-        return AVERROR_PATCHWELCOME;
-    }
     if (asclen <= 0)
         return AVERROR_INVALIDDATA;
-    bits_consumed = decode_audio_specific_config(NULL, avctx, &m4ac,
-                                         gb->buffer + (config_start_bit / 8),
-                                         asclen, sync_extension);
 
-    if (bits_consumed < 0)
+    init_get_bits(&gbc, gb->buffer, config_start_bit + asclen);
+    skip_bits_long(&gbc, config_start_bit);
+
+    bits_consumed = decode_audio_specific_config_gb(NULL, avctx, &m4ac,
+                                                    &gbc, config_start_bit,
+                                                    sync_extension);
+
+    if (bits_consumed < config_start_bit)
         return AVERROR_INVALIDDATA;
+    bits_consumed -= config_start_bit;
 
     if (!latmctx->initialized ||
         ac->oc[1].m4ac.sample_rate != m4ac.sample_rate ||
@@ -329,7 +330,10 @@ static int latm_decode_audio_specific_config(struct LATMContext *latmctx,
         }
 
         avctx->extradata_size = esize;
-        memcpy(avctx->extradata, gb->buffer + (config_start_bit/8), esize);
+        gbc = *gb;
+        for (i = 0; i < esize; i++) {
+          avctx->extradata[i] = get_bits(&gbc, 8);
+        }
         memset(avctx->extradata+esize, 0, AV_INPUT_BUFFER_PADDING_SIZE);
     }
     skip_bits_long(gb, bits_consumed);

libavcodec/aacdec_template.c

@@ -715,6 +715,13 @@ static void decode_channel_map(uint8_t layout_map[][3],
     }
 }
 
+static inline void relative_align_get_bits(GetBitContext *gb,
+                                           int reference_position) {
+    int n = (reference_position - get_bits_count(gb) & 7);
+    if (n)
+        skip_bits(gb, n);
+}
+
 /**
  * Decode program configuration element; reference: table 4.2.
  *
@@ -722,7 +729,7 @@ static void decode_channel_map(uint8_t layout_map[][3],
  */
 static int decode_pce(AVCodecContext *avctx, MPEG4AudioConfig *m4ac,
                       uint8_t (*layout_map)[3],
-                      GetBitContext *gb)
+                      GetBitContext *gb, int byte_align_ref)
 {
     int num_front, num_side, num_back, num_lfe, num_assoc_data, num_cc;
     int sampling_index;
@@ -770,7 +777,7 @@ static int decode_pce(AVCodecContext *avctx, MPEG4AudioConfig *m4ac,
     decode_channel_map(layout_map + tags, AAC_CHANNEL_CC,    gb, num_cc);
     tags += num_cc;
 
-    align_get_bits(gb);
+    relative_align_get_bits(gb, byte_align_ref);
 
     /* comment field, first byte is length */
     comment_len = get_bits(gb, 8) * 8;
@@ -792,6 +799,7 @@ static int decode_pce(AVCodecContext *avctx, MPEG4AudioConfig *m4ac,
  */
 static int decode_ga_specific_config(AACContext *ac, AVCodecContext *avctx,
                                      GetBitContext *gb,
+                                     int get_bit_alignment,
                                      MPEG4AudioConfig *m4ac,
                                      int channel_config)
 {
@@ -815,7 +823,7 @@ static int decode_ga_specific_config(AACContext *ac, AVCodecContext *avctx,
 
     if (channel_config == 0) {
         skip_bits(gb, 4);  // element_instance_tag
-        tags = decode_pce(avctx, m4ac, layout_map, gb);
+        tags = decode_pce(avctx, m4ac, layout_map, gb, get_bit_alignment);
         if (tags < 0)
             return tags;
     } else {
@@ -937,37 +945,25 @@ static int decode_eld_specific_config(AACContext *ac, AVCodecContext *avctx,
  * @param   ac          pointer to AACContext, may be null
  * @param   avctx       pointer to AVCCodecContext, used for logging
  * @param   m4ac        pointer to MPEG4AudioConfig, used for parsing
- * @param   data        pointer to buffer holding an audio specific config
- * @param   bit_size    size of audio specific config or data in bits
+ * @param   gb          buffer holding an audio specific config
+ * @param   get_bit_alignment relative alignment for byte align operations
  * @param   sync_extension look for an appended sync extension
  *
  * @return  Returns error status or number of consumed bits. <0 - error
  */
-static int decode_audio_specific_config(AACContext *ac,
+static int decode_audio_specific_config_gb(AACContext *ac,
                                            AVCodecContext *avctx,
                                            MPEG4AudioConfig *m4ac,
-                                        const uint8_t *data, int64_t bit_size,
+                                           GetBitContext *gb,
+                                           int get_bit_alignment,
                                            int sync_extension)
 {
-    GetBitContext gb;
     int i, ret;
+    GetBitContext gbc = *gb;
 
-    if (bit_size < 0 || bit_size > INT_MAX) {
-        av_log(avctx, AV_LOG_ERROR, "Audio specific config size is invalid\n");
+    if ((i = ff_mpeg4audio_get_config_gb(m4ac, &gbc, sync_extension)) < 0)
         return AVERROR_INVALIDDATA;
-    }
 
-    ff_dlog(avctx, "audio specific config size %d\n", (int)bit_size >> 3);
-    for (i = 0; i < bit_size >> 3; i++)
-        ff_dlog(avctx, "%02x ", data[i]);
-    ff_dlog(avctx, "\n");
-
-    if ((ret = init_get_bits(&gb, data, bit_size)) < 0)
-        return ret;
-
-    if ((i = avpriv_mpeg4audio_get_config(m4ac, data, bit_size,
-                                          sync_extension)) < 0)
-        return AVERROR_INVALIDDATA;
     if (m4ac->sampling_index > 12) {
         av_log(avctx, AV_LOG_ERROR,
                "invalid sampling rate index %d\n",
@@ -982,7 +978,7 @@ static int decode_audio_specific_config(AACContext *ac,
         return AVERROR_INVALIDDATA;
     }
 
-    skip_bits_long(&gb, i);
+    skip_bits_long(gb, i);
 
     switch (m4ac->object_type) {
     case AOT_AAC_MAIN:
@@ -990,12 +986,12 @@ static int decode_audio_specific_config(AACContext *ac,
     case AOT_AAC_LTP:
     case AOT_ER_AAC_LC:
     case AOT_ER_AAC_LD:
-        if ((ret = decode_ga_specific_config(ac, avctx, &gb,
+        if ((ret = decode_ga_specific_config(ac, avctx, gb, get_bit_alignment,
                                             m4ac, m4ac->chan_config)) < 0)
             return ret;
         break;
     case AOT_ER_AAC_ELD:
-        if ((ret = decode_eld_specific_config(ac, avctx, &gb,
+        if ((ret = decode_eld_specific_config(ac, avctx, gb,
                                               m4ac, m4ac->chan_config)) < 0)
             return ret;
         break;
@@ -1013,7 +1009,33 @@ static int decode_audio_specific_config(AACContext *ac,
             m4ac->sample_rate, m4ac->sbr,
             m4ac->ps);
 
-    return get_bits_count(&gb);
+    return get_bits_count(gb);
+}
+
+static int decode_audio_specific_config(AACContext *ac,
+                                        AVCodecContext *avctx,
+                                        MPEG4AudioConfig *m4ac,
+                                        const uint8_t *data, int64_t bit_size,
+                                        int sync_extension)
+{
+    int i, ret;
+    GetBitContext gb;
+
+    if (bit_size < 0 || bit_size > INT_MAX) {
+        av_log(avctx, AV_LOG_ERROR, "Audio specific config size is invalid\n");
+        return AVERROR_INVALIDDATA;
+    }
+
+    ff_dlog(avctx, "audio specific config size %d\n", (int)bit_size >> 3);
+    for (i = 0; i < bit_size >> 3; i++)
+        ff_dlog(avctx, "%02x ", data[i]);
+    ff_dlog(avctx, "\n");
+
+    if ((ret = init_get_bits(&gb, data, bit_size)) < 0)
+        return ret;
+
+    return decode_audio_specific_config_gb(ac, avctx, m4ac, &gb, 0,
+                                           sync_extension);
 }
 
 /**
@@ -3003,7 +3025,7 @@ static int aac_decode_frame_int(AVCodecContext *avctx, void *data,
             uint8_t layout_map[MAX_ELEM_ID*4][3];
             int tags;
             push_output_configuration(ac);
-            tags = decode_pce(avctx, &ac->oc[1].m4ac, layout_map, gb);
+            tags = decode_pce(avctx, &ac->oc[1].m4ac, layout_map, gb, 0);
             if (tags < 0) {
                 err = tags;
                 break;

libavcodec/mpeg4audio.c

@@ -83,70 +83,62 @@ static inline int get_sample_rate(GetBitContext *gb, int *index)
         avpriv_mpeg4audio_sample_rates[*index];
 }
 
-int avpriv_mpeg4audio_get_config(MPEG4AudioConfig *c, const uint8_t *buf,
-                                 int bit_size, int sync_extension)
+int ff_mpeg4audio_get_config_gb(MPEG4AudioConfig *c, GetBitContext *gb,
+                                int sync_extension)
 {
-    GetBitContext gb;
     int specific_config_bitindex, ret;
-
-    if (bit_size <= 0)
-        return AVERROR_INVALIDDATA;
-
-    ret = init_get_bits(&gb, buf, bit_size);
-    if (ret < 0)
-        return ret;
-
-    c->object_type = get_object_type(&gb);
-    c->sample_rate = get_sample_rate(&gb, &c->sampling_index);
-    c->chan_config = get_bits(&gb, 4);
+    int start_bit_index = get_bits_count(gb);
+    c->object_type = get_object_type(gb);
+    c->sample_rate = get_sample_rate(gb, &c->sampling_index);
+    c->chan_config = get_bits(gb, 4);
     if (c->chan_config < FF_ARRAY_ELEMS(ff_mpeg4audio_channels))
         c->channels = ff_mpeg4audio_channels[c->chan_config];
     c->sbr = -1;
     c->ps  = -1;
     if (c->object_type == AOT_SBR || (c->object_type == AOT_PS &&
         // check for W6132 Annex YYYY draft MP3onMP4
-        !(show_bits(&gb, 3) & 0x03 && !(show_bits(&gb, 9) & 0x3F)))) {
+        !(show_bits(gb, 3) & 0x03 && !(show_bits(gb, 9) & 0x3F)))) {
         if (c->object_type == AOT_PS)
             c->ps = 1;
         c->ext_object_type = AOT_SBR;
         c->sbr = 1;
-        c->ext_sample_rate = get_sample_rate(&gb, &c->ext_sampling_index);
-        c->object_type = get_object_type(&gb);
+        c->ext_sample_rate = get_sample_rate(gb, &c->ext_sampling_index);
+        c->object_type = get_object_type(gb);
         if (c->object_type == AOT_ER_BSAC)
-            c->ext_chan_config = get_bits(&gb, 4);
+            c->ext_chan_config = get_bits(gb, 4);
     } else {
         c->ext_object_type = AOT_NULL;
         c->ext_sample_rate = 0;
     }
-    specific_config_bitindex = get_bits_count(&gb);
+    specific_config_bitindex = get_bits_count(gb);
 
     if (c->object_type == AOT_ALS) {
-        skip_bits(&gb, 5);
-        if (show_bits_long(&gb, 24) != MKBETAG('\0','A','L','S'))
-            skip_bits_long(&gb, 24);
+        skip_bits(gb, 5);
+        if (show_bits_long(gb, 24) != MKBETAG('\0','A','L','S'))
+            skip_bits_long(gb, 24);
 
-        specific_config_bitindex = get_bits_count(&gb);
+        specific_config_bitindex = get_bits_count(gb);
 
-        ret = parse_config_ALS(&gb, c);
+        ret = parse_config_ALS(gb, c);
         if (ret < 0)
             return ret;
     }
 
     if (c->ext_object_type != AOT_SBR && sync_extension) {
-        while (get_bits_left(&gb) > 15) {
-            if (show_bits(&gb, 11) == 0x2b7) { // sync extension
-                get_bits(&gb, 11);
-                c->ext_object_type = get_object_type(&gb);
-                if (c->ext_object_type == AOT_SBR && (c->sbr = get_bits1(&gb)) == 1) {
-                    c->ext_sample_rate = get_sample_rate(&gb, &c->ext_sampling_index);
+        while (get_bits_left(gb) > 15) {
+            if (show_bits(gb, 11) == 0x2b7) { // sync extension
+                get_bits(gb, 11);
+                c->ext_object_type = get_object_type(gb);
+                if (c->ext_object_type == AOT_SBR && (c->sbr = get_bits1(gb)) == 1) {
+                    c->ext_sample_rate = get_sample_rate(gb, &c->ext_sampling_index);
                     if (c->ext_sample_rate == c->sample_rate)
                         c->sbr = -1;
                 }
-                if (get_bits_left(&gb) > 11 && get_bits(&gb, 11) == 0x548)
-                    c->ps = get_bits1(&gb);
+                if (get_bits_left(gb) > 11 && get_bits(gb, 11) == 0x548)
+                    c->ps = get_bits1(gb);
                 break;
             } else
-                get_bits1(&gb); // skip 1 bit
+                get_bits1(gb); // skip 1 bit
         }
     }
 
@@ -157,7 +149,23 @@ int avpriv_mpeg4audio_get_config(MPEG4AudioConfig *c, const uint8_t *buf,
     if ((c->ps == -1 && c->object_type != AOT_AAC_LC) || c->channels & ~0x01)
         c->ps = 0;
 
-    return specific_config_bitindex;
+    return specific_config_bitindex - start_bit_index;
+}
+
+int avpriv_mpeg4audio_get_config(MPEG4AudioConfig *c, const uint8_t *buf,
+                                 int bit_size, int sync_extension)
+{
+    GetBitContext gb;
+    int ret;
+
+    if (bit_size <= 0)
+        return AVERROR_INVALIDDATA;
+
+    ret = init_get_bits(&gb, buf, bit_size);
+    if (ret < 0)
+        return ret;
+
+    return ff_mpeg4audio_get_config_gb(c, &gb, sync_extension);
 }
 
 static av_always_inline unsigned int copy_bits(PutBitContext *pb,

libavcodec/mpeg4audio.h

@@ -45,7 +45,17 @@ extern av_export const int avpriv_mpeg4audio_sample_rates[16];
 extern const uint8_t ff_mpeg4audio_channels[8];
 
 /**
- * Parse MPEG-4 systems extradata to retrieve audio configuration.
+ * Parse MPEG-4 systems extradata from a potentially unaligned GetBitContext to retrieve audio configuration.
+ * @param[in] c        MPEG4AudioConfig structure to fill.
+ * @param[in] gb       Extradata from container.
+ * @param[in] sync_extension look for a sync extension after config if true.
+ * @return On error -1 is returned, on success AudioSpecificConfig bit index in extradata.
+ */
+int ff_mpeg4audio_get_config_gb(MPEG4AudioConfig *c, GetBitContext *gb,
+                                int sync_extension);
+
+/**
+ * Parse MPEG-4 systems extradata from a raw buffer to retrieve audio configuration.
  * @param[in] c        MPEG4AudioConfig structure to fill.
  * @param[in] buf      Extradata from container.
  * @param[in] bit_size Extradata size in bits.