lavfi/libplacebo: support dovi metadata application

libplacebo supports automatic dolby vision application, but it requires
us to switch to a new API. Also add some logic to strip the dolby vision
metadata from the output frames in any case where we end up changing the
colorimetry.

The libplacebo dependency bump is justified because neither 184 nor 192
are part of any stable libplacebo release, so users have to build from
git anyways for this filter to exist.

Signed-off-by: Niklas Haas <git@haasn.dev>

2 files changed, 33 insertions, 4 deletions

diff --git a/configure b/configure
index 729e9b5ac7..30e6ba3883 100755
--- a/configure
+++ b/configure
@@ -6586,7 +6586,7 @@ enabled libopus           && {
         require_pkg_config libopus opus opus_multistream.h opus_multistream_surround_encoder_create
     }
 }
-enabled libplacebo        && require_pkg_config libplacebo "libplacebo >= 4.184.0" libplacebo/vulkan.h pl_vulkan_create
+enabled libplacebo        && require_pkg_config libplacebo "libplacebo >= 4.192.0" libplacebo/vulkan.h pl_vulkan_create
 enabled libpulse          && require_pkg_config libpulse libpulse pulse/pulseaudio.h pa_context_new
 enabled librabbitmq       && require_pkg_config librabbitmq "librabbitmq >= 0.7.1" amqp.h amqp_new_connection
 enabled librav1e          && require_pkg_config librav1e "rav1e >= 0.4.0" rav1e.h rav1e_context_new
diff --git a/libavfilter/vf_libplacebo.c b/libavfilter/vf_libplacebo.c
index 5b1e7b5285..1386aaeb3a 100644
--- a/libavfilter/vf_libplacebo.c
+++ b/libavfilter/vf_libplacebo.c
@@ -47,6 +47,7 @@ typedef struct LibplaceboContext {
     int force_divisible_by;
     int normalize_sar;
     int apply_filmgrain;
+    int apply_dovi;
     int colorspace;
     int color_range;
     int color_primaries;
@@ -281,8 +282,16 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out, AVFrame *in)
     LibplaceboContext *s = avctx->priv;
     struct pl_render_params params;
     struct pl_frame image, target;
-    ok = pl_map_avframe(s->gpu, &image, NULL, in);
-    ok &= pl_map_avframe(s->gpu, &target, NULL, out);
+    ok = pl_map_avframe_ex(s->gpu, &image, pl_avframe_params(
+        .frame    = in,
+        .map_dovi = s->apply_dovi,
+    ));
+
+    ok &= pl_map_avframe_ex(s->gpu, &target, pl_avframe_params(
+        .frame    = out,
+        .map_dovi = false,
+    ));
+
     if (!ok) {
         err = AVERROR_EXTERNAL;
         goto fail;
@@ -381,7 +390,7 @@ fail:
 
 static int filter_frame(AVFilterLink *link, AVFrame *in)
 {
-    int err;
+    int err, changed;
     AVFilterContext *ctx = link->dst;
     LibplaceboContext *s = ctx->priv;
     AVFilterLink *outlink = ctx->outputs[0];
@@ -400,6 +409,14 @@ static int filter_frame(AVFilterLink *link, AVFrame *in)
     out->width = outlink->w;
     out->height = outlink->h;
 
+    if (s->apply_dovi && av_frame_get_side_data(in, AV_FRAME_DATA_DOVI_METADATA)) {
+        /* Output of dovi reshaping is always BT.2020+PQ, so infer the correct
+         * output colorspace defaults */
+        out->colorspace = AVCOL_SPC_BT2020_NCL;
+        out->color_primaries = AVCOL_PRI_BT2020;
+        out->color_trc = AVCOL_TRC_SMPTE2084;
+    }
+
     if (s->colorspace >= 0)
         out->colorspace = s->colorspace;
     if (s->color_range >= 0)
@@ -411,6 +428,17 @@ static int filter_frame(AVFilterLink *link, AVFrame *in)
 
     RET(process_frames(ctx, out, in));
 
+    int changed_csp = s->colorspace      != out->colorspace     ||
+                      s->color_range     != out->color_range    ||
+                      s->color_trc       != out->color_trc      ||
+                      s->color_primaries != out->color_primaries;
+
+    if (s->apply_dovi || changed_csp) {
+        /* Strip side data if no longer relevant */
+        av_frame_remove_side_data(out, AV_FRAME_DATA_DOVI_RPU_BUFFER);
+        av_frame_remove_side_data(out, AV_FRAME_DATA_DOVI_METADATA);
+    }
+
     if (s->apply_filmgrain)
         av_frame_remove_side_data(out, AV_FRAME_DATA_FILM_GRAIN_PARAMS);
 
@@ -559,6 +587,7 @@ static const AVOption libplacebo_options[] = {
     { "antiringing", "Antiringing strength (for non-EWA filters)", OFFSET(antiringing), AV_OPT_TYPE_FLOAT, {.dbl = 0.0}, 0.0, 1.0, DYNAMIC },
     { "sigmoid", "Enable sigmoid upscaling", OFFSET(sigmoid), AV_OPT_TYPE_BOOL, {.i64 = 1}, 0, 1, DYNAMIC },
     { "apply_filmgrain", "Apply film grain metadata", OFFSET(apply_filmgrain), AV_OPT_TYPE_BOOL, {.i64 = 1}, 0, 1, DYNAMIC },
+    { "apply_dolbyvision", "Apply Dolby Vision metadata", OFFSET(apply_dovi), AV_OPT_TYPE_BOOL, {.i64 = 1}, 0, 1, DYNAMIC },
 
     { "deband", "Enable debanding", OFFSET(deband), AV_OPT_TYPE_BOOL, {.i64 = 0}, 0, 1, DYNAMIC },
     { "deband_iterations", "Deband iterations", OFFSET(deband_iterations), AV_OPT_TYPE_INT, {.i64 = 1}, 0, 16, DYNAMIC },