truehd_core: Switch to in-place modifications

The truehd_core bitstream filter decreases the sizes of the
major_sync_info structure (if present), of the
substream_directory and of the substreams themselves. As a consequence,
there is enough space available in front of the actual substream data
for the new header, so that one only needs to modify the header in front
of the actual data (which apart from shrinking is left untouched) and
the packet's size and buffer pointer (after having made sure that the
packet is writable).

This and switching to bsf_get_packet_ref also removed the need for
having separate packets for in- and output.

Even if the input is not writable, there are noticable performance
improvements: The average of 10 iterations of processing a file with 262144
runs each (inlcuding about 20 skips per iteration) went down from 5669
to 4362 decicycles. If the input is writable, it goes down to 1363
decicycles.
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>

libavcodec/truehd_core_bsf.c

@@ -36,34 +36,33 @@ typedef struct TrueHDCoreContext {
     MLPHeaderInfo hdr;
 } TrueHDCoreContext;
 
-static int truehd_core_filter(AVBSFContext *ctx, AVPacket *out)
+static int truehd_core_filter(AVBSFContext *ctx, AVPacket *pkt)
 {
     TrueHDCoreContext *s = ctx->priv_data;
     GetBitContext gbc;
     AccessUnit units[MAX_SUBSTREAMS];
-    AVPacket *in;
     int ret, i, last_offset = 0;
     int in_size, out_size;
     int have_header = 0;
     int substream_bytes = 0;
     int end;
 
-    ret = ff_bsf_get_packet(ctx, &in);
+    ret = ff_bsf_get_packet_ref(ctx, pkt);
     if (ret < 0)
         return ret;
 
-    if (in->size < 4) {
+    if (pkt->size < 4) {
         ret = AVERROR_INVALIDDATA;
         goto fail;
     }
 
-    in_size = (AV_RB16(in->data) & 0xFFF) * 2;
-    if (in_size < 4 || in_size > in->size) {
+    in_size = (AV_RB16(pkt->data) & 0xFFF) * 2;
+    if (in_size < 4 || in_size > pkt->size) {
         ret = AVERROR_INVALIDDATA;
         goto fail;
     }
 
-    ret = init_get_bits8(&gbc, in->data + 4, in->size - 4);
+    ret = init_get_bits8(&gbc, pkt->data + 4, pkt->size - 4);
     if (ret < 0)
         goto fail;
 
@@ -99,27 +98,31 @@ static int truehd_core_filter(AVBSFContext *ctx, AVPacket *out)
     out_size = end + 4 + last_offset;
     if (out_size < in_size) {
         int bpos = 0, reduce = end - have_header * 28 - substream_bytes;
-        uint16_t parity_nibble, dts = AV_RB16(in->data + 2);
+        uint16_t parity_nibble, dts = AV_RB16(pkt->data + 2);
         uint16_t auheader;
+        uint8_t header[28];
 
-        av_assert1(reduce % 2 == 0);
+        av_assert1(reduce >= 0 && reduce % 2 == 0);
 
-        ret = av_new_packet(out, out_size);
+        if (have_header) {
+            memcpy(header, pkt->data + 4, 28);
+            header[16]  = (header[16] & 0x0c) | (FFMIN(s->hdr.num_substreams, 3) << 4);
+            header[17] &= 0x7f;
+            header[25] &= 0xfe;
+            AV_WL16(header + 26, ff_mlp_checksum16(header, 26));
+        }
+
+        pkt->data += reduce;
+        out_size  -= reduce;
+        pkt->size  = out_size;
+
+        ret = av_packet_make_writable(pkt);
         if (ret < 0)
             goto fail;
 
-        AV_WB16(out->data + 2, dts);
+        AV_WB16(pkt->data + 2, dts);
         parity_nibble = dts;
-        out->size     -= reduce;
-        parity_nibble ^= out->size / 2;
-
-        if (have_header) {
-            memcpy(out->data + 4, in->data + 4, 28);
-            out->data[16 + 4] = (out->data[16 + 4] & 0x0c) | (FFMIN(s->hdr.num_substreams, 3) << 4);
-            out->data[17 + 4]&= 0x7f;
-            out->data[25 + 4] = out->data[25 + 4] & 0xfe;
-            AV_WL16(out->data + 4 + 26, ff_mlp_checksum16(out->data + 4, 26));
-        }
+        parity_nibble ^= out_size / 2;
 
         for (i = 0; i < FFMIN(s->hdr.num_substreams, 3); i++) {
             uint16_t substr_hdr = 0;
@@ -130,13 +133,13 @@ static int truehd_core_filter(AVBSFContext *ctx, AVPacket *out)
             substr_hdr |= (units[i].bits[3] << 12);
             substr_hdr |=  units[i].offset;
 
-            AV_WB16(out->data + have_header * 28 + 4 + bpos, substr_hdr);
+            AV_WB16(pkt->data + have_header * 28 + 4 + bpos, substr_hdr);
 
             parity_nibble ^= substr_hdr;
             bpos          += 2;
 
             if (units[i].bits[0]) {
-                AV_WB16(out->data + have_header * 28 + 4 + bpos, units[i].optional);
+                AV_WB16(pkt->data + have_header * 28 + 4 + bpos, units[i].optional);
 
                 parity_nibble ^= units[i].optional;
                 bpos          += 2;
@@ -147,22 +150,17 @@ static int truehd_core_filter(AVBSFContext *ctx, AVPacket *out)
         parity_nibble ^= parity_nibble >> 4;
         parity_nibble &= 0xF;
 
-        memcpy(out->data + have_header * 28 + 4 + bpos,
-               in->data + 4 + end,
-               out_size - (4 + end));
         auheader  = (parity_nibble ^ 0xF) << 12;
-        auheader |= (out->size / 2) & 0x0fff;
-        AV_WB16(out->data, auheader);
+        auheader |= (out_size / 2) & 0x0fff;
+        AV_WB16(pkt->data, auheader);
 
-        ret = av_packet_copy_props(out, in);
-    } else {
-        av_packet_move_ref(out, in);
+        if (have_header)
+            memcpy(pkt->data + 4, header, 28);
     }
 
 fail:
     if (ret < 0)
-        av_packet_unref(out);
-    av_packet_free(&in);
+        av_packet_unref(pkt);
 
     return ret;
 }