diff --git a/crates/pf-capture/src/lib.rs b/crates/pf-capture/src/lib.rs index ea3af07d..938bdd6f 100644 --- a/crates/pf-capture/src/lib.rs +++ b/crates/pf-capture/src/lib.rs @@ -254,6 +254,54 @@ pub struct ZeroCopyPolicy { pub fn capturer_supports_444(_encoder_ingests_rgb_444: bool) -> bool { true } + +/// Whether the **native-plane** capturer (a compositor virtual output) can deliver an HDR (10-bit +/// PQ/BT.2020) source on this platform — the capture-side gate the punktfunk/1 handshake consults +/// before negotiating 10-bit (mirroring [`capturer_supports_444`]). +/// +/// Linux: `false`. GNOME 50 added HDR **screen sharing** for *monitor* streams only — Mutter's +/// `RecordVirtual` virtual-monitor streams advertise 8-bit BGRx/BGRA exclusively (still true on +/// the GNOME 51 dev branch), and virtual outputs report no BT2020/PQ colour capabilities, so they +/// can't be flipped into HDR mode via DisplayConfig either. The Linux HDR path that DOES exist — +/// the GNOME 50+ portal **monitor mirror** (`open_portal_monitor` with `want_hdr`) — is gated +/// separately by the GameStream plane (`host_hdr_capable` + the live monitor colour-mode probe). +#[cfg(target_os = "linux")] +pub fn capturer_supports_hdr() -> bool { + false +} +/// Windows: the IDD-push capturer proactively enables advanced colour and delivers P010/Rgb10a2. +#[cfg(target_os = "windows")] +pub fn capturer_supports_hdr() -> bool { + true +} +#[cfg(not(any(target_os = "linux", target_os = "windows")))] +pub fn capturer_supports_hdr() -> bool { + false +} + +/// Process-wide latch: a `want_hdr` portal capture failed to negotiate the HDR (10-bit PQ) offer — +/// the compositor never accepted it (monitor left HDR mode between the probe and the negotiation, +/// NVIDIA EGL not listing LINEAR for XR30, a pre-50 Mutter…). Later sessions consult +/// [`hdr_capture_failed`] and fall back to the SDR offer instead of re-running the same doomed +/// 10-second negotiation timeout on every reconnect. Sticky until host restart (matching the +/// zero-copy downgrade latches); the log line at latch time says so. +#[cfg(target_os = "linux")] +static HDR_CAPTURE_FAILED: std::sync::atomic::AtomicBool = std::sync::atomic::AtomicBool::new(false); + +#[cfg(target_os = "linux")] +pub fn hdr_capture_failed() -> bool { + HDR_CAPTURE_FAILED.load(std::sync::atomic::Ordering::Relaxed) +} + +#[cfg(target_os = "linux")] +pub(crate) fn note_hdr_capture_failed() { + if !HDR_CAPTURE_FAILED.swap(true, std::sync::atomic::Ordering::Relaxed) { + tracing::warn!( + "HDR capture negotiation failed — this host will offer SDR capture for the rest of \ + the process lifetime (restart the host after fixing the monitor's HDR mode to retry)" + ); + } +} #[cfg(target_os = "windows")] pub fn capturer_supports_444(encoder_ingests_rgb_444: bool) -> bool { // IDD-push delivers full-chroma BGRA for an SDR 4:4:4 session (skipping the NV12 VideoConverter), @@ -316,16 +364,28 @@ pub use idd_push::verify_is_wudfhost; #[cfg(target_os = "linux")] #[path = "linux/mod.rs"] mod linux; +// The GNOME BT.2100 colour-mode probe — the host's capture-side gate for offering HDR on the +// portal monitor path (see `open_portal_monitor`'s `want_hdr`). +#[cfg(target_os = "linux")] +pub use linux::gnome_hdr_monitor_active; #[cfg(target_os = "windows")] #[path = "windows/synthetic_nv12.rs"] pub mod synthetic_nv12; /// Open the Linux xdg-ScreenCast portal capturer for a client-sized monitor. `anchored` drives -/// ScreenCast off a RemoteDesktop session (KWin/GNOME) so it inherits that grant headlessly. The -/// [`ZeroCopyPolicy`] carries the pre-resolved encode-backend facts (the one-way edge). +/// ScreenCast off a RemoteDesktop session (KWin/GNOME) so it inherits that grant headlessly. +/// `want_hdr` offers the GNOME 50+ HDR formats (10-bit PQ/BT.2020 dmabufs) instead of the SDR +/// set — pass it only when the mirrored monitor is actually in HDR mode (the host probes +/// DisplayConfig) or the negotiation runs into its 10 s timeout and latches the SDR downgrade. +/// The [`ZeroCopyPolicy`] carries the pre-resolved encode-backend facts (the one-way edge). #[cfg(target_os = "linux")] -pub fn open_portal_monitor(anchored: bool, policy: ZeroCopyPolicy) -> Result> { - linux::PortalCapturer::open(anchored, policy).map(|c| Box::new(c) as Box) +pub fn open_portal_monitor( + anchored: bool, + want_hdr: bool, + policy: ZeroCopyPolicy, +) -> Result> { + linux::PortalCapturer::open(anchored, want_hdr && !hdr_capture_failed(), policy) + .map(|c| Box::new(c) as Box) } /// Open the Linux portal capturer bound to an already-created virtual output's PipeWire node. The diff --git a/crates/pf-capture/src/linux/mod.rs b/crates/pf-capture/src/linux/mod.rs index 5eae5cac..e019c9a9 100644 --- a/crates/pf-capture/src/linux/mod.rs +++ b/crates/pf-capture/src/linux/mod.rs @@ -62,6 +62,13 @@ pub struct PortalCapturer { /// the process-wide downgrade ([`pf_zerocopy::note_vaapi_dmabuf_failed`]) so the pipeline /// rebuild retries on the CPU offer instead of failing identically forever. vaapi_dmabuf: bool, + /// This capture ran the HDR (10-bit PQ/BT.2020 dmabuf) offer — see [`Self::open`]'s + /// `want_hdr`. Read by the negotiation-timeout diagnosis (a failed HDR offer latches the + /// process-wide SDR downgrade) and by [`hdr_meta`](Capturer::hdr_meta). + hdr_offer: bool, + /// Set once the stream negotiated one of the 10-bit PQ formats (`param_changed`), i.e. frames + /// really are PQ/BT.2020 — drives [`hdr_meta`](Capturer::hdr_meta). + hdr_negotiated: Arc, /// The PipeWire node this capturer consumes — surfaced in error messages for diagnosis. node_id: u32, /// Stops the PipeWire loop on teardown (sent in `Drop`). Without it a dropped or failed @@ -80,8 +87,9 @@ pub struct PortalCapturer { impl PortalCapturer { /// `anchored` drives ScreenCast off a RemoteDesktop session (KWin/GNOME) so it inherits the /// RemoteDesktop grant and never raises a separate ScreenCast dialog; `false` uses a plain - /// ScreenCast session (wlroots, which has no RemoteDesktop portal). - pub fn open(anchored: bool, policy: ZeroCopyPolicy) -> Result { + /// ScreenCast session (wlroots, which has no RemoteDesktop portal). `want_hdr` offers the + /// GNOME 50+ HDR formats (10-bit PQ/BT.2020, dmabuf-only) instead of the SDR set. + pub fn open(anchored: bool, want_hdr: bool, policy: ZeroCopyPolicy) -> Result { // Portal handshake (async) on its own thread; hands back the PW fd + node id. let (setup_tx, setup_rx) = std::sync::mpsc::channel::>(); thread::Builder::new() @@ -102,11 +110,12 @@ impl PortalCapturer { }; tracing::info!( node_id, + want_hdr, "ScreenCast portal session started; connecting PipeWire" ); // This portal path (GameStream / monitor capture) is always 4:2:0, so allow zero-copy as before. Ok( - spawn_pipewire(Some(fd), node_id, None, true, false, policy)? + spawn_pipewire(Some(fd), node_id, None, true, false, want_hdr, policy)? .into_capturer(node_id, None), ) } @@ -135,12 +144,15 @@ impl PortalCapturer { want_444, "connecting PipeWire to virtual output" ); + // Virtual outputs are SDR-only upstream (Mutter's RecordVirtual streams advertise 8-bit + // BGRx/BGRA exclusively, GNOME 50 and 51-dev alike) — never run the HDR offer here. Ok(spawn_pipewire( remote_fd, node_id, preferred_mode, allow_zerocopy, want_444, + false, policy, )? .into_capturer(node_id, Some(keepalive))) @@ -160,6 +172,10 @@ struct PwHandles { /// This capture will offer LINEAR-dmabuf-only for the VAAPI passthrough (see /// [`PortalCapturer::vaapi_dmabuf`]). vaapi_dmabuf: bool, + /// This capture ran the HDR offer (see [`PortalCapturer::hdr_offer`]). + hdr_offer: bool, + /// See [`PortalCapturer::hdr_negotiated`]. + hdr_negotiated: Arc, quit: ::pipewire::channel::Sender<()>, join: thread::JoinHandle<()>, } @@ -177,6 +193,8 @@ impl PwHandles { broken: self.broken, stall_since: None, vaapi_dmabuf: self.vaapi_dmabuf, + hdr_offer: self.hdr_offer, + hdr_negotiated: self.hdr_negotiated, node_id, quit: Some(self.quit), join: Some(self.join), @@ -199,6 +217,10 @@ fn spawn_pipewire( // 4:4:4 session: tiled dmabufs convert to planar YUV444 on the GPU (`ImportKind::Tiled444`) // instead of NV12/RGB, so the session stays zero-copy at full chroma. want_444: bool, + // HDR session (GNOME 50+ monitor mirror): offer ONLY the 10-bit PQ/BT.2020 formats as + // LINEAR dmabufs (SHM can't carry them — Mutter's SHM record path paints 8-bit ARGB32 + // regardless of the negotiated format, and the tiled EGL de-tile blit is 8-bit). + want_hdr: bool, // Encode-backend facts resolved by the facade (never re-derived here) — the one-way // capture→encode edge (plan §W6). policy: ZeroCopyPolicy, @@ -213,17 +235,29 @@ fn spawn_pipewire( let streaming_cb = streaming.clone(); let broken = Arc::new(AtomicBool::new(false)); let broken_cb = broken.clone(); + let hdr_negotiated = Arc::new(AtomicBool::new(false)); + let hdr_negotiated_cb = hdr_negotiated.clone(); // pipewire's own cross-thread channel: the receiver attaches to the loop and quits it; the // sender lives on the capturer and fires in its `Drop`. Absolute `::pipewire` path — the // inner `mod pipewire` shadows the crate name at this scope. let (quit_tx, quit_rx) = ::pipewire::channel::channel::<()>(); let zerocopy = allow_zerocopy && pf_zerocopy::enabled(); + // HDR cannot ride the SHM path (see `want_hdr` above): under PUNKTFUNK_FORCE_SHM the HDR + // offer is dropped — SDR capture, loudly. + let force_shm = std::env::var("PUNKTFUNK_FORCE_SHM").as_deref() == Ok("1"); + let want_hdr = if want_hdr && force_shm { + tracing::warn!( + "HDR capture requested but PUNKTFUNK_FORCE_SHM=1 — the SHM path is 8-bit only; \ + offering SDR" + ); + false + } else { + want_hdr + }; // Mirror of the thread's `vaapi_passthrough` decision (deterministic from here: on a VAAPI // backend the EGL→CUDA importer is never built) — kept on the capturer so `next_frame`'s // negotiation-timeout branch knows a failed negotiation was the LINEAR-dmabuf offer. - let vaapi_dmabuf = zerocopy - && std::env::var("PUNKTFUNK_FORCE_SHM").as_deref() != Ok("1") - && policy.backend_is_vaapi; + let vaapi_dmabuf = zerocopy && !force_shm && policy.backend_is_vaapi; let join = thread::Builder::new() .name("punktfunk-pipewire".into()) .spawn(move || { @@ -235,8 +269,10 @@ fn spawn_pipewire( negotiated_cb, streaming_cb, broken_cb, + hdr_negotiated_cb, zerocopy, want_444, + want_hdr, preferred, quit_rx, policy, @@ -252,6 +288,8 @@ fn spawn_pipewire( streaming, broken, vaapi_dmabuf, + hdr_offer: want_hdr, + hdr_negotiated, quit: quit_tx, join, }) @@ -354,6 +392,26 @@ impl Capturer for PortalCapturer { fn set_active(&self, active: bool) { self.active.store(active, Ordering::Relaxed); } + + /// Generic HDR10 mastering metadata once the stream negotiated a 10-bit PQ format. Mutter + /// exposes no per-monitor mastering volume through the screencast, so this is the standard + /// HDR10 default block (BT.2020 primaries, D65 white, 1000 / 0.005 cd/m², CLL unknown) — the + /// same fallback Windows uses when a display reports nothing. The native stream loop prefers + /// the client display's own volume when the client sent one (`Hello::display_hdr`). + fn hdr_meta(&self) -> Option { + if !self.hdr_negotiated.load(Ordering::Relaxed) { + return None; + } + Some(punktfunk_core::quic::HdrMeta { + // ST.2086 order G, B, R; (x, y) chromaticity in 1/50000 units. + display_primaries: [[8500, 39850], [6550, 2300], [35400, 14600]], + white_point: [15635, 16450], // D65 + max_display_mastering_luminance: 10_000_000, // 1000 cd/m² (0.0001 units) + min_display_mastering_luminance: 50, // 0.005 cd/m² + max_cll: 0, + max_fall: 0, + }) + } } impl PortalCapturer { @@ -372,6 +430,20 @@ impl PortalCapturer { or capture never started)", self.node_id )) + } else if self.hdr_offer { + // The HDR (10-bit PQ dmabuf) offer was never accepted — the monitor left HDR + // mode between the probe and the negotiation, the compositor pre-dates the + // GNOME 50 HDR formats, or its allocator can't do LINEAR for XR30/XB30. + // Latch the process-wide SDR downgrade so the next session (Moonlight + // auto-reconnects) negotiates SDR instead of re-running this same timeout. + super::note_hdr_capture_failed(); + Err(anyhow!( + "no PipeWire frame within 10s (node {}): the compositor never accepted \ + the HDR (10-bit PQ/BT.2020 dmabuf) offer — is the mirrored monitor in \ + HDR mode on GNOME 50+? Downgrading this host to SDR capture; reconnect \ + to stream SDR", + self.node_id + )) } else if self.vaapi_dmabuf && !pf_zerocopy::vaapi_dmabuf_forced() { // The LINEAR-dmabuf-only offer (VAAPI passthrough default) was never accepted. // Latch the process-wide downgrade so the encode loop's pipeline rebuild @@ -416,6 +488,85 @@ impl Drop for PortalCapturer { } } +/// Whether any monitor of the live GNOME session is currently in BT.2100 (HDR) colour mode — the +/// precondition for Mutter's monitor screencast advertising the 10-bit PQ formats (GNOME 50+; +/// Mutter only appends the HDR formats while the mirrored monitor's colour state is BT.2020+PQ). +/// Queried over the session bus: `DisplayConfig.GetCurrentState`, monitor property +/// `"color-mode" == 1` (`META_COLOR_MODE_BT2100`). `false` on any error — not GNOME, a pre-48 +/// Mutter without colour modes, no monitors — so callers fall back to the honest SDR offer. +/// Blocking (one D-Bus round-trip on a fresh connection); call from control-plane threads only. +pub fn gnome_hdr_monitor_active() -> bool { + use ashpd::zbus; + // GetCurrentState reply: (serial, monitors, logical_monitors, properties); each monitor is + // (spec(ssss), modes a(siiddada{sv}), properties a{sv}) — "color-mode" lives in the monitor + // properties. + type Mode = ( + String, + i32, + i32, + f64, + f64, + Vec, + std::collections::HashMap, + ); + type Monitor = ( + (String, String, String, String), + Vec, + std::collections::HashMap, + ); + type LogicalMonitor = ( + i32, + i32, + f64, + u32, + bool, + Vec<(String, String, String, String)>, + std::collections::HashMap, + ); + type State = ( + u32, + Vec, + Vec, + std::collections::HashMap, + ); + let probe = || -> Result { + // zbus is built async-only here (ashpd's tokio integration) — run the one round-trip on + // a throwaway current-thread runtime; this is a control-plane call, never per-frame. + let rt = tokio::runtime::Builder::new_current_thread() + .enable_all() + .build() + .context("build tokio runtime")?; + rt.block_on(async { + let conn = zbus::Connection::session().await.context("session bus")?; + let reply = conn + .call_method( + Some("org.gnome.Mutter.DisplayConfig"), + "/org/gnome/Mutter/DisplayConfig", + Some("org.gnome.Mutter.DisplayConfig"), + "GetCurrentState", + &(), + ) + .await + .context("DisplayConfig.GetCurrentState")?; + let (_serial, monitors, _logical, _props): State = + reply.body().deserialize().context("parse GetCurrentState")?; + Ok(monitors.iter().any(|(_spec, _modes, props)| { + props + .get("color-mode") + .and_then(|v| u32::try_from(v).ok()) + .is_some_and(|mode| mode == 1) // META_COLOR_MODE_BT2100 + })) + }) + }; + match probe() { + Ok(hdr) => hdr, + Err(e) => { + tracing::debug!(error = %format!("{e:#}"), "GNOME HDR colour-mode probe failed — SDR"); + false + } + } +} + /// Pick the ScreenCast cursor mode from what the backend advertises (`AvailableCursorModes`), /// preferring **cursor-as-metadata**: the compositor keeps its cheap hardware cursor plane and /// ships the pointer as PipeWire `SPA_META_Cursor` metadata (position + an occasional bitmap), @@ -669,6 +820,10 @@ mod pipewire { VideoFormat::RGBA => PixelFormat::Rgba, VideoFormat::RGB => PixelFormat::Rgb, VideoFormat::BGR => PixelFormat::Bgr, + // The GNOME 50+ HDR screencast formats (packed 2:10:10:10; only ever negotiated by + // the `want_hdr` offer, whose MANDATORY colorimetry props pin them to PQ/BT.2020). + VideoFormat::xRGB_210LE => PixelFormat::X2Rgb10, + VideoFormat::xBGR_210LE => PixelFormat::X2Bgr10, _ => return None, }) } @@ -732,6 +887,9 @@ mod pipewire { /// irrecoverably gone for this stream — the import worker died, or tiled imports failed /// [`IMPORT_FAIL_POISON`] times in a row. broken: Arc, + /// Set when the negotiated format is one of the 10-bit PQ formats (`param_changed`) — + /// read by [`PortalCapturer::hdr_meta`](super::PortalCapturer). + hdr_negotiated: Arc, /// Consecutive tiled-import failures (reset on success); see [`IMPORT_FAIL_POISON`]. import_fail_streak: u32, /// Present when zero-copy is enabled on NVIDIA: imports a dmabuf → CUDA device buffer, @@ -886,6 +1044,80 @@ mod pipewire { serialize_pod(obj) } + /// Build one GNOME 50+ HDR format pod: `format` (xRGB_210LE / xBGR_210LE) as a LINEAR-only + /// dmabuf with **MANDATORY** BT.2020 primaries + SMPTE ST.2084 (PQ) transfer-function props — + /// the exact colorimetry Mutter's monitor stream advertises while the mirrored monitor is in + /// HDR mode (its HDR pods carry the same props MANDATORY, so both sides must speak them for + /// the intersection to exist; an SDR or pre-50 producer can never match this pod). + /// + /// LINEAR-only because every 10-bit consumer we have reads the buffer without a de-tile pass: + /// the CPU path mmaps it, and the VAAPI passthrough imports it into a VA surface. The tiled + /// EGL de-tile blit renders into an 8-bit `GL_RGBA8` texture — it would silently crush the + /// depth — so tiled modifiers are deliberately NOT advertised (a zero-copy 10-bit de-tile is + /// the follow-up). SHM is excluded entirely: Mutter's SHM record path paints 8-bit ARGB32 + /// regardless of the negotiated format. + fn build_hdr_dmabuf_format( + format: VideoFormat, + preferred: Option<(u32, u32, u32)>, + ) -> Result> { + let (dw, dh, dhz) = preferred.unwrap_or((1920, 1080, 60)); + use pw::spa::param::format::{FormatProperties, MediaSubtype, MediaType}; + let mut obj = pw::spa::pod::object!( + pw::spa::utils::SpaTypes::ObjectParamFormat, + pw::spa::param::ParamType::EnumFormat, + pw::spa::pod::property!(FormatProperties::MediaType, Id, MediaType::Video), + pw::spa::pod::property!(FormatProperties::MediaSubtype, Id, MediaSubtype::Raw), + pw::spa::pod::property!(FormatProperties::VideoFormat, Id, format), + pw::spa::pod::property!( + FormatProperties::VideoSize, + Choice, + Range, + Rectangle, + pw::spa::utils::Rectangle { + width: dw, + height: dh + }, + pw::spa::utils::Rectangle { + width: 1, + height: 1 + }, + pw::spa::utils::Rectangle { + width: 8192, + height: 8192 + } + ), + pw::spa::pod::property!( + FormatProperties::VideoFramerate, + Choice, + Range, + Fraction, + pw::spa::utils::Fraction { num: dhz, denom: 1 }, + pw::spa::utils::Fraction { num: 0, denom: 1 }, + pw::spa::utils::Fraction { num: 240, denom: 1 } + ), + ); + obj.properties.push(pw::spa::pod::Property { + key: pw::spa::sys::SPA_FORMAT_VIDEO_modifier, + flags: pw::spa::pod::PropertyFlags::MANDATORY, + value: pw::spa::pod::Value::Long(0), // DRM_FORMAT_MOD_LINEAR + }); + obj.properties.push(pw::spa::pod::Property { + key: pw::spa::sys::SPA_FORMAT_VIDEO_transferFunction, + flags: pw::spa::pod::PropertyFlags::MANDATORY, + value: pw::spa::pod::Value::Id(pw::spa::utils::Id( + pw::spa::sys::SPA_VIDEO_TRANSFER_SMPTE2084, + )), + }); + obj.properties.push(pw::spa::pod::Property { + key: pw::spa::sys::SPA_FORMAT_VIDEO_colorPrimaries, + flags: pw::spa::pod::PropertyFlags::MANDATORY, + value: pw::spa::pod::Value::Id(pw::spa::utils::Id( + pw::spa::sys::SPA_VIDEO_COLOR_PRIMARIES_BT2020, + )), + }); + serialize_pod(obj) + } + /// The default (shm/CPU-path) format offer: raw video in any encoder-mappable layout, any /// size, any framerate (0/1 = variable allowed — gamescope fixates exactly that). fn build_default_format_obj(preferred: Option<(u32, u32, u32)>) -> pw::spa::pod::Object { @@ -1157,6 +1389,54 @@ mod pipewire { }) } + /// Alpha-blend the cached cursor bitmap into a packed 10-bit (`X2Rgb10`/`X2Bgr10`) CPU frame: + /// unpack each u32, blend the 8-bit cursor channels scaled to 10 bits (`v<<2 | v>>6`), repack. + /// The frame samples are PQ-encoded, so like the 8-bit gamma-space blend this is a display- + /// referred approximation — fine for a cursor. `r_shift` is the R channel's bit offset (20 for + /// x:R:G:B, 0 for x:B:G:R); G is always at 10 and B mirrors R. + fn composite_cursor_rgb10( + tight: &mut [u8], + w: usize, + h: usize, + r_shift: u32, + cursor: &CursorState, + ) { + let b_shift = 20 - r_shift; // 0 or 20 — the opposite end from R + let (bw, bh) = (cursor.bw as i32, cursor.bh as i32); + for cy in 0..bh { + let dy = cursor.y + cy; + if dy < 0 || dy as usize >= h { + continue; + } + for cx in 0..bw { + let dx = cursor.x + cx; + if dx < 0 || dx as usize >= w { + continue; + } + let s = ((cy * bw + cx) as usize) * 4; + let a = cursor.rgba[s + 3] as u32; + if a == 0 { + continue; + } + // 8-bit cursor channel → 10-bit (replicate the top bits into the bottom). + let up10 = |v: u8| ((v as u32) << 2) | ((v as u32) >> 6); + let (sr, sg, sb) = ( + up10(cursor.rgba[s]), + up10(cursor.rgba[s + 1]), + up10(cursor.rgba[s + 2]), + ); + let di = (dy as usize * w + dx as usize) * 4; + let px = u32::from_le_bytes(tight[di..di + 4].try_into().unwrap()); + let blend = |dst: u32, src: u32| (src * a + dst * (255 - a)) / 255; + let dr = blend((px >> r_shift) & 0x3ff, sr); + let dg = blend((px >> 10) & 0x3ff, sg); + let db = blend((px >> b_shift) & 0x3ff, sb); + let out = (px & 0xc000_0000) | (dr << r_shift) | (dg << 10) | (db << b_shift); + tight[di..di + 4].copy_from_slice(&out.to_le_bytes()); + } + } + } + /// Alpha-blend the cached cursor bitmap into the tightly-packed CPU frame at its latched /// position. Cheap: a straight-alpha blit over at most ~256×256 pixels, clipped to the frame — /// the whole point of cursor-as-metadata (no forced full-frame composite on the producer). @@ -1170,6 +1450,12 @@ mod pipewire { if !cursor.visible || cursor.rgba.is_empty() { return; } + // The packed 10-bit HDR layouts blend via bit unpack/repack, not byte offsets. + match fmt { + PixelFormat::X2Rgb10 => return composite_cursor_rgb10(tight, w, h, 20, cursor), + PixelFormat::X2Bgr10 => return composite_cursor_rgb10(tight, w, h, 0, cursor), + _ => {} + } let Some((ri, gi, bi, bpp)) = dst_offsets(fmt) else { return; }; @@ -1344,7 +1630,10 @@ mod pipewire { // through to the shm de-pad copy below. let mut gpu_import_broken = false; if let (Some(importer), Some(fmt)) = (ud.importer.as_mut(), ud.format) { - if datas[0].type_() == pw::spa::buffer::DataType::DmaBuf { + // Defense-in-depth: the 10-bit PQ formats must never enter the EGL→CUDA import (its + // de-tile blit is 8-bit RGBA8 — silent depth loss). An HDR offer never builds the + // importer, so this gate only matters if those invariants ever drift apart. + if datas[0].type_() == pw::spa::buffer::DataType::DmaBuf && !fmt.is_hdr_rgb10() { let plane = pf_zerocopy::DmabufPlane { fd: datas[0].fd(), offset: datas[0].chunk().offset(), @@ -1604,9 +1893,13 @@ mod pipewire { negotiated: Arc, streaming: Arc, broken: Arc, + hdr_negotiated: Arc, zerocopy: bool, // 4:4:4 session: tiled dmabufs take the worker's planar-YUV444 GPU convert. want_444: bool, + // HDR session: offer ONLY the 10-bit PQ/BT.2020 formats as LINEAR dmabufs (see + // `build_hdr_dmabuf_format`); the SDR offers are not built at all. + want_hdr: bool, preferred: Option<(u32, u32, u32)>, quit_rx: pw::channel::Receiver<()>, // Encode-backend facts resolved by the facade (never re-derived here) — the one-way @@ -1645,7 +1938,10 @@ mod pipewire { // succeed and produce CUDA payloads the VAAPI encoder must reject. Also skipped once // repeated worker deaths latched the import off (a wedged GPU stack must not crash-loop). let backend_is_vaapi = policy.backend_is_vaapi; - let mut importer = if zerocopy && !backend_is_vaapi { + // HDR never builds the EGL→CUDA importer: its de-tile blit renders into 8-bit RGBA8, + // which would silently crush the 10-bit depth. The HDR consumers are the CPU mmap path + // (LINEAR de-pad → X2Rgb10 CPU frames) and the VAAPI raw-dmabuf passthrough. + let mut importer = if zerocopy && !backend_is_vaapi && !want_hdr { if pf_zerocopy::gpu_import_disabled() { tracing::warn!( "zero-copy GPU import disabled after repeated import-worker deaths — using CPU path" @@ -1755,6 +2051,7 @@ mod pipewire { negotiated, streaming, broken, + hdr_negotiated, import_fail_streak: 0, importer, vaapi_passthrough, @@ -1822,12 +2119,20 @@ mod pipewire { let sz = ud.info.size(); ud.format = map_format(ud.info.format()); ud.modifier = ud.info.modifier(); + // HDR: the 10-bit PQ formats are only ever offered with MANDATORY BT.2020/PQ + // colorimetry props, so a 10-bit negotiation IS an HDR negotiation — but log + // what the producer actually fixated for diagnosis. + let hdr = ud.format.is_some_and(|f| f.is_hdr_rgb10()); + ud.hdr_negotiated.store(hdr, Ordering::Relaxed); tracing::info!( width = sz.width, height = sz.height, spa_format = ?ud.info.format(), mapped = ?ud.format, modifier = ud.modifier, + hdr, + transfer_function = ud.info.transfer_function(), + color_primaries = ud.info.color_primaries(), "pipewire format negotiated" ); if ud.format.is_none() { @@ -2029,20 +2334,36 @@ mod pipewire { // (offering shm too makes the compositor pick shm). The modifier list is advertised with // DONT_FIXATE so the compositor's allocator chooses one; we re-emit the fixated format in // `param_changed` (the two-step DMA-BUF handshake). Otherwise offer the multi-format shm - // pod and let MAP_BUFFERS map it. - let shm_values = serialize_pod(obj)?; - let (dmabuf_values, buffers_values) = if want_dmabuf { - ( - Some(build_dmabuf_format(&modifiers, preferred)?), - Some(build_dmabuf_buffers()?), - ) + // pod and let MAP_BUFFERS map it. An HDR session replaces ALL of this with the two 10-bit + // PQ pods (LINEAR dmabuf, MANDATORY colorimetry — see `build_hdr_dmabuf_format`): offering + // SDR alongside would make the producer pick its earlier-listed SDR format, and the + // negotiation-timeout path latches the process-wide SDR downgrade if nothing matches. + let format_pods: Vec> = if want_hdr { + tracing::info!( + "HDR capture: offering xRGB_210LE/xBGR_210LE LINEAR dmabufs with MANDATORY \ + BT.2020 + SMPTE-2084 (PQ) colorimetry (GNOME 50+ monitor stream)" + ); + vec![ + build_hdr_dmabuf_format(VideoFormat::xRGB_210LE, preferred)?, + build_hdr_dmabuf_format(VideoFormat::xBGR_210LE, preferred)?, + ] + } else if want_dmabuf { + vec![build_dmabuf_format(&modifiers, preferred)?] + } else { + vec![serialize_pod(obj)?] + }; + let buffers_values = if want_hdr || want_dmabuf { + // Dmabuf-only. For HDR this is load-bearing beyond zero-copy: Mutter's SHM record + // path paints 8-bit ARGB32 regardless of the negotiated format, so a MemFd buffer + // under a 10-bit format would carry mislabeled bytes. + Some(build_dmabuf_buffers()?) } else if force_shm { // True SHM: exclude DmaBuf so Mutter MUST download (glReadPixels orders against render). - (None, Some(build_shm_only_buffers()?)) + Some(build_shm_only_buffers()?) } else { // CPU path still accepts mappable dmabufs (gamescope offers only those once its // modifier-bearing format pod wins the intersection). - (None, Some(build_mappable_buffers()?)) + Some(build_mappable_buffers()?) }; // Ask for cursor-as-metadata on every path (harmless if the producer can't supply it): the @@ -2050,9 +2371,8 @@ mod pipewire { // compositor keeps its cheap hardware cursor plane (see `choose_cursor_mode`). let cursor_meta = build_cursor_meta_param()?; let mut byte_slices: Vec<&[u8]> = Vec::new(); - match &dmabuf_values { - Some(d) => byte_slices.push(d), - None => byte_slices.push(&shm_values), + for pod in &format_pods { + byte_slices.push(pod); } if let Some(b) = &buffers_values { byte_slices.push(b); diff --git a/crates/pf-encode/src/enc/linux/mod.rs b/crates/pf-encode/src/enc/linux/mod.rs index 140e9296..7224c0ce 100644 --- a/crates/pf-encode/src/enc/linux/mod.rs +++ b/crates/pf-encode/src/enc/linux/mod.rs @@ -27,8 +27,8 @@ use super::libav::{ use ffmpeg::ffi; // = ffmpeg_sys_next /// The swscale *source* pixel format for a captured packed RGB/BGR layout (the real byte order, not -/// the NVENC-padded `*0` form). Used by the 4:4:4 RGB→YUV444P conversion path. Mirrors the VAAPI -/// CPU-input mapping; YUV/10-bit inputs can't feed this path (the 4:4:4 session forces packed RGB). +/// the NVENC-padded `*0` form). Used by the CPU conversion paths: 4:4:4 RGB→YUV444P, and HDR +/// X2RGB10/X2BGR10→P010. Mirrors the VAAPI CPU-input mapping; YUV inputs can't feed this path. fn sws_src_pixel(format: PixelFormat) -> Result { Ok(match format { PixelFormat::Bgrx => Pixel::BGRZ, // bgr0 @@ -37,8 +37,12 @@ fn sws_src_pixel(format: PixelFormat) -> Result { PixelFormat::Rgba => Pixel::RGBA, PixelFormat::Rgb => Pixel::RGB24, PixelFormat::Bgr => Pixel::BGR24, + // The GNOME 50+ HDR capture formats (PQ/BT.2020 packed 2:10:10:10) — the HDR CPU path's + // swscale source for the X2RGB10→P010 conversion. + PixelFormat::X2Rgb10 => Pixel::X2RGB10LE, + PixelFormat::X2Bgr10 => Pixel::X2BGR10LE, PixelFormat::Nv12 | PixelFormat::P010 | PixelFormat::Rgb10a2 | PixelFormat::Yuv444 => { - bail!("NVENC 4:4:4 CPU-input path supports packed RGB/BGR only; got {format:?}") + bail!("NVENC CPU-input conversion supports packed RGB/BGR only; got {format:?}") } }) } @@ -136,6 +140,9 @@ fn nvenc_input(format: PixelFormat) -> (Pixel, bool) { // the Windows paths; the Linux capturer never emits them. Map to BGRA so the match is // exhaustive — unreachable here. PixelFormat::Rgb10a2 | PixelFormat::P010 => (Pixel::BGRA, false), + // The Linux HDR capture formats never take the RGB-passthrough input: `open` intercepts + // them onto the X2RGB10→P010 swscale path before consulting this mapping (like 4:4:4). + PixelFormat::X2Rgb10 | PixelFormat::X2Bgr10 => (Pixel::BGRA, false), } } @@ -164,11 +171,12 @@ pub struct NvencEncoder { frame: Option, /// Zero-copy path: CUDA hwdevice/hwframes contexts (the encoder takes `AV_PIX_FMT_CUDA`). cuda: Option, - /// 4:4:4 CPU path only: swscale context converting the captured packed RGB/BGR → planar - /// YUV444P into [`Self::frame`], because `hevc_nvenc` only emits 4:4:4 from a YUV444 *input* - /// (RGB-in is always 4:2:0). `None` on the 4:2:0 paths AND on the zero-copy 4:4:4 path (the - /// worker's GPU convert delivers YUV444 CUDA frames). Freed in `Drop`. - sws_444: Option<*mut ffi::SwsContext>, + /// CPU CSC paths only: swscale context converting the captured packed source into + /// [`Self::frame`] — RGB/BGR → planar YUV444P for a 4:4:4 session (`hevc_nvenc` only emits + /// 4:4:4 from a YUV444 *input*; RGB-in is always 4:2:0), or X2RGB10/X2BGR10 → P010 (BT.2020 + /// limited) for an HDR session. `None` on the plain RGB paths AND on the zero-copy paths (the + /// worker's GPU convert delivers ready CUDA frames). Freed in `Drop`. + sws_csc: Option<*mut ffi::SwsContext>, /// This session opened as full-chroma 4:4:4 (FREXT) — via either input path. want_444: bool, src_format: PixelFormat, @@ -191,7 +199,7 @@ pub struct NvencEncoder { args: OpenArgs, } -// `CudaHw` holds raw `AVBufferRef`s and `sws_444` a raw `SwsContext`; the encoder lives on a single +// `CudaHw` holds raw `AVBufferRef`s and `sws_csc` a raw `SwsContext`; the encoder lives on a single // thread. The CPU encoder is already `Send` via ffmpeg-next; assert it for the raw fields too. // SAFETY: `NvencEncoder` owns an ffmpeg-next `Encoder`/`VideoFrame` (already `Send`) plus a `CudaHw` // holding raw `AVBufferRef`s and an optional raw `SwsContext`, none of which are `Send` by default. @@ -247,14 +255,27 @@ impl NvencEncoder { bit_depth: u8, chroma: ChromaFormat, ) -> Result { - // TODO(hdr): Linux 10-bit parity. Unlike the Windows raw-SDK path (which upconverts 8-bit - // ARGB → Main10 via pixelBitDepthMinus8), libavcodec hevc_nvenc needs a 10-bit input pixel - // format (p010) for Main10, so it's a bigger change; deferred until a Linux GPU box is - // available to validate. The Linux host stays 8-bit for now. - if bit_depth != 8 { + // HDR / 10-bit (GNOME 50+ HDR screencast): a 10-bit session whose capture negotiated a + // packed 2:10:10:10 PQ/BT.2020 format (`X2Rgb10`/`X2Bgr10`) encodes HEVC Main10 / 10-bit + // AV1 from a P010 input frame we produce by swscale (BT.2020 limited; the PQ transfer + // rides through per-channel — BT.2020 NCL Y'CbCr *is* derived from the PQ-encoded R'G'B'). + // A 10-bit request whose capture stayed SDR (HDR offer downgraded) honestly encodes 8-bit. + let want_hdr10 = bit_depth == 10 && format.is_hdr_rgb10() && codec.supports_10bit(); + if bit_depth == 10 && !want_hdr10 { tracing::warn!( bit_depth, - "Linux NVENC 10-bit not yet wired — encoding 8-bit" + ?format, + codec = codec.nvenc_name(), + "10-bit requested but the capture format/codec has no 10-bit path — encoding 8-bit" + ); + } + if format.is_hdr_rgb10() && !want_hdr10 { + // A 10-bit PQ capture on an 8-bit session would be encoded with a BT.709 VUI and + // garbage bit-packing — never silently; the session must renegotiate. + bail!( + "captured 10-bit HDR frames ({format:?}) on an 8-bit/{} session — refusing to \ + mislabel PQ content", + codec.nvenc_name() ); } // Full-chroma 4:4:4 (HEVC Range Extensions). `hevc_nvenc` only emits 4:4:4 from a YUV444 @@ -263,6 +284,11 @@ impl NvencEncoder { // (planar-YUV444 CUDA frames — `cuda` true), or the CPU path's swscale RGB→YUV444P. Both // feed `profile=rext`; the range follows `PUNKTFUNK_444_FULLRANGE` in both. let want_444 = chroma.is_444() && codec == Codec::H265; + if want_444 && want_hdr10 { + // The handshake resolves 4:4:4∧10-bit down to 8-bit on Linux, so this can't happen — + // fail loudly if it ever does rather than picking one silently. + bail!("4:4:4 + 10-bit HDR is not a supported Linux NVENC combination"); + } ffmpeg::init().context("ffmpeg init")?; if std::env::var_os("PUNKTFUNK_FFMPEG_DEBUG").is_some() { // SAFETY: `av_log_set_level` sets libav's global integer log level; `48` (= AV_LOG_DEBUG) @@ -274,10 +300,13 @@ impl NvencEncoder { let av_codec = encoder::find_by_name(name) .ok_or_else(|| anyhow!("{name} not built into libavcodec"))?; let (rgb_pixel, rgb_expand) = nvenc_input(format); - // 4:4:4 feeds NVENC a planar YUV444P frame we produce by swscale; the ordinary path feeds the - // captured RGB straight in and lets NVENC's internal CSC subsample to 4:2:0. + // 4:4:4 feeds NVENC a planar YUV444P frame we produce by swscale; HDR feeds it a P010 + // frame likewise; the ordinary path feeds the captured RGB straight in and lets NVENC's + // internal CSC subsample to 4:2:0. let (nvenc_pixel, expand) = if want_444 { (Pixel::YUV444P, false) + } else if want_hdr10 { + (Pixel::P010LE, false) } else { (rgb_pixel, rgb_expand) }; @@ -325,7 +354,21 @@ impl NvencEncoder { // visible win. Linux-only: the Windows path's NVENC-internal CSC range is unmeasured. let full_range_444 = want_444 && std::env::var("PUNKTFUNK_444_FULLRANGE").is_ok_and(|v| v.trim() == "1"); - if matches!(format, PixelFormat::Nv12) || want_444 { + if want_hdr10 { + // HDR10: BT.2020 primaries + SMPTE-2084 (PQ) transfer, limited range — matches the + // swscale BT.2020 CSC below and the Windows paths' signalling. The client decoder + // auto-detects PQ from the VUI; static mastering metadata rides out-of-band. + // SAFETY: `raw = video.as_mut_ptr()` is the non-null, properly-aligned, sole-owned, + // not-yet-opened `AVCodecContext`; we set its four VUI colour enum fields to valid + // variants before `open_with`. Sole owner → no aliasing; synchronous writes. + unsafe { + let raw = video.as_mut_ptr(); + (*raw).colorspace = ffi::AVColorSpace::AVCOL_SPC_BT2020_NCL; + (*raw).color_range = ffi::AVColorRange::AVCOL_RANGE_MPEG; + (*raw).color_primaries = ffi::AVColorPrimaries::AVCOL_PRI_BT2020; + (*raw).color_trc = ffi::AVColorTransferCharacteristic::AVCOL_TRC_SMPTE2084; + } + } else if matches!(format, PixelFormat::Nv12) || want_444 { // SAFETY: same `video` builder — `raw = video.as_mut_ptr()` is the non-null, properly- // aligned, sole-owned, not-yet-opened `AVCodecContext`. We set its four VUI colour enum // fields to valid `AVColorSpace`/`AVColorRange`/`AVColorPrimaries`/`AVColorTransfer- @@ -370,17 +413,20 @@ impl NvencEncoder { None }; - // 4:4:4 CPU path: build the RGB→YUV444P swscale (BT.709, range per the flag; no rescale). - // Mirrors the VAAPI CPU path's RGB→NV12 scaler, but the dst is full-chroma planar 4:4:4. - // Skipped on the zero-copy path (`cuda`): the worker's GPU convert already delivers - // planar YUV444 CUDA frames — no CPU pixels exist to scale. - let sws_444 = if want_444 && !cuda { + // CPU CSC paths: build the packed-RGB → planar swscale (no rescale) into the encoder's + // input frame. Two users: 4:4:4 (RGB→YUV444P, BT.709, range per the flag) and HDR + // (X2RGB10/X2BGR10→P010, BT.2020 limited — the PQ transfer is per-channel and rides + // through the matrix untouched). Skipped on the zero-copy path (`cuda`): the worker's GPU + // convert already delivers ready CUDA frames — no CPU pixels exist to scale. + let sws_csc = if (want_444 || want_hdr10) && !cuda { let src_av = pixel_to_av(sws_src_pixel(format)?); + let dst_av = pixel_to_av(nvenc_pixel); // SAFETY: `sws_getContext` allocates a swscale context for the given src/dst dims + pixel // formats. Both dims are the encoder's positive `width`/`height` as `c_int`; `src_av` is a - // valid `AVPixelFormat` (from the `sws_src_pixel`-validated, packed-RGB-only source), the - // dst is YUV444P. The trailing filter/param pointers are null = "use defaults" (documented - // as accepted). No Rust memory is borrowed; the returned pointer is null-checked below. + // valid `AVPixelFormat` (from the `sws_src_pixel`-validated packed-RGB source), the dst is + // YUV444P (4:4:4) or P010LE (HDR). The trailing filter/param pointers are null = "use + // defaults" (documented as accepted). No Rust memory is borrowed; the returned pointer is + // null-checked below. let sws = unsafe { ffi::sws_getContext( width as c_int, @@ -388,7 +434,7 @@ impl NvencEncoder { src_av, width as c_int, height as c_int, - ffi::AVPixelFormat::AV_PIX_FMT_YUV444P, + dst_av, SWS_POINT, ptr::null_mut(), ptr::null_mut(), @@ -396,17 +442,22 @@ impl NvencEncoder { ) }; if sws.is_null() { - bail!("sws_getContext(RGB→YUV444P) failed"); + bail!("sws_getContext(RGB→{nvenc_pixel:?}) failed"); } - // SAFETY: `sws` is the non-null context from the call above (null-checked). The ITU-709 - // coefficient table from `sws_getCoefficients` is a process-lifetime libswscale static, - // reused for src+dst matrices; `sws_setColorspaceDetails` only reads it and writes scalar - // CSC settings into `sws` (dstRange matches the VUI: 0 = limited, 1 = the - // PUNKTFUNK_444_FULLRANGE experiment). No Rust memory is passed. + // SAFETY: `sws` is the non-null context from the call above (null-checked). The + // coefficient tables from `sws_getCoefficients` (ITU-709 for 4:4:4, BT.2020 NCL for HDR + // — matching the VUI written above) are process-lifetime libswscale statics, reused for + // src+dst matrices; `sws_setColorspaceDetails` only reads them and writes scalar CSC + // settings into `sws` (dstRange matches the VUI: 0 = limited, 1 = the + // PUNKTFUNK_444_FULLRANGE experiment; HDR is always limited). No Rust memory is passed. unsafe { - let cs709 = ffi::sws_getCoefficients(SWS_CS_ITU709); + let cs = ffi::sws_getCoefficients(if want_hdr10 { + super::libav::SWS_CS_BT2020 + } else { + SWS_CS_ITU709 + }); let dst_range = i32::from(full_range_444); - ffi::sws_setColorspaceDetails(sws, cs709, 1, cs709, dst_range, 0, 1 << 16, 1 << 16); + ffi::sws_setColorspaceDetails(sws, cs, 1, cs, dst_range, 0, 1 << 16, 1 << 16); } Some(sws) } else { @@ -432,6 +483,12 @@ impl NvencEncoder { // dropped on a future libavcodec. opts.set("profile", "rext"); } + if want_hdr10 && codec == Codec::H265 { + // HEVC Main10. `hevc_nvenc` auto-selects it from the P010 input, but pin it explicitly + // so the depth is never silently dropped on a future libavcodec. (10-bit AV1 needs no + // profile — AV1 Main carries 10-bit, driven by the input format.) + opts.set("profile", "main10"); + } // Split-frame encode across both NVENC engines (GB203 has 2) when the pixel rate exceeds // a single engine's HEVC capacity (~1 Gpix/s); e.g. 5120x1440@240 = 1.77 Gpix/s needs it, @@ -501,7 +558,7 @@ impl NvencEncoder { enc, frame, cuda: cuda_hw, - sws_444, + sws_csc, want_444, src_format: format, expand, @@ -640,7 +697,7 @@ impl NvencEncoder { ); // 4:4:4: swscale the packed RGB straight into the planar YUV444P input frame (BT.709 limited), // then send it — no byte-expand. The 4:2:0 RGB path (below) feeds NVENC packed RGB directly. - if let Some(sws) = self.sws_444 { + if let Some(sws) = self.sws_csc { let frame = self .frame .as_mut() @@ -810,7 +867,7 @@ impl NvencEncoder { impl Drop for NvencEncoder { fn drop(&mut self) { - if let Some(sws) = self.sws_444.take() { + if let Some(sws) = self.sws_csc.take() { // SAFETY: `sws` is the non-null `SwsContext` allocated by `sws_getContext` in `open` and // owned exclusively by this encoder (taken out of the field so it can't be freed twice). // `sws_freeContext` frees it; nothing else references it after this single-threaded drop. @@ -855,3 +912,105 @@ pub fn probe_can_encode_444(codec: Codec) -> bool { unsafe { ffi::av_log_set_level(prev) }; ok } + +#[cfg(test)] +mod hdr_tests { + use super::*; + + /// The Linux HDR (GNOME 50 portal) encode path end-to-end on a real NVIDIA GPU: a synthetic + /// PQ-ish X2RGB10 CPU frame → swscale BT.2020 → P010 → `hevc_nvenc` Main10, drained to a real + /// AU. `#[ignore]`d (needs NVENC): + /// `cargo test -p pf-encode nvenc_hdr10_smoke -- --ignored --nocapture` + #[test] + #[ignore] + fn nvenc_hdr10_smoke() { + let (w, h) = (640u32, 480u32); + let mut enc = NvencEncoder::open( + Codec::H265, + PixelFormat::X2Rgb10, + w, + h, + 30, + 2_000_000, + false, + 10, + ChromaFormat::Yuv420, + ) + .expect("open hevc_nvenc Main10 (P010 input)"); + // Packed x:R:G:B 2:10:10:10 gradient (values are treated as PQ-encoded — fine for a smoke). + let mut bytes = vec![0u8; (w * h * 4) as usize]; + for y in 0..h { + for x in 0..w { + let r = (x * 1023 / w.max(1)) & 0x3ff; + let g = (y * 1023 / h.max(1)) & 0x3ff; + let b = ((x + y) * 1023 / (w + h)) & 0x3ff; + let px: u32 = (r << 20) | (g << 10) | b; + let i = ((y * w + x) * 4) as usize; + bytes[i..i + 4].copy_from_slice(&px.to_le_bytes()); + } + } + let frame = CapturedFrame { + width: w, + height: h, + pts_ns: 0, + format: PixelFormat::X2Rgb10, + payload: FramePayload::Cpu(bytes), + cursor: None, + }; + let mut au = None; + for _ in 0..30 { + enc.submit(&frame).expect("submit X2Rgb10 frame"); + if let Some(a) = enc.poll().expect("poll") { + au = Some(a); + break; + } + } + let au = au.expect("no AU produced within 30 frames"); + assert!(!au.data.is_empty(), "empty AU"); + assert!(au.keyframe, "first AU should be the IDR"); + println!("HDR10 smoke: first AU {} bytes (IDR)", au.data.len()); + // PF_HDR_SMOKE_DUMP=/path.h265: write the Annex-B AU for external inspection — + // `ffprobe -show_streams` should report Main 10, bt2020nc/smpte2084/bt2020 colours. + if let Ok(path) = std::env::var("PF_HDR_SMOKE_DUMP") { + std::fs::write(&path, &au.data).expect("dump AU"); + println!("HDR10 smoke: AU written to {path}"); + } + } +} + +/// Probe whether this NVIDIA GPU + driver + libavcodec can actually encode 10-bit (HEVC Main10 / +/// 10-bit AV1) from a P010 input — the exact path [`NvencEncoder::open`] takes for a live HDR +/// stream (a tiny X2RGB10-sourced, P010-input open). The result is cached by the caller +/// ([`crate::can_encode_10bit`]); a GPU/driver/ffmpeg without the 10-bit encode fails the open +/// here, so the host resolves the session to 8-bit SDR before the Welcome (honest downgrade). +pub fn probe_can_encode_10bit(codec: Codec) -> bool { + if !codec.supports_10bit() { + return false; + } + if ffmpeg::init().is_err() { + return false; + } + // Quiet ffmpeg's open error on a GPU that lacks 10-bit — the probe failing is an expected outcome. + // SAFETY: libav initialized above; `av_log_{get,set}_level` only read/write the global int level + // (no pointer args) and are always sound post-init. + let prev = unsafe { + let p = ffi::av_log_get_level(); + ffi::av_log_set_level(ffi::AV_LOG_FATAL); + p + }; + let ok = NvencEncoder::open( + codec, + PixelFormat::X2Rgb10, + 640, + 480, + 30, + 2_000_000, + false, // CPU input (the HDR swscale path) + 10, + ChromaFormat::Yuv420, + ) + .is_ok(); + // SAFETY: restore the saved global log level (scalar arg, no pointers). + unsafe { ffi::av_log_set_level(prev) }; + ok +} diff --git a/crates/pf-encode/src/enc/linux/nvenc_cuda.rs b/crates/pf-encode/src/enc/linux/nvenc_cuda.rs index 418f9c88..dc8828fd 100644 --- a/crates/pf-encode/src/enc/linux/nvenc_cuda.rs +++ b/crates/pf-encode/src/enc/linux/nvenc_cuda.rs @@ -474,9 +474,13 @@ impl NvencCudaEncoder { // clear reason instead of an opaque session error on the first frame. try_api().map_err(|e| anyhow!("NVENC (Linux direct) unavailable: {e}"))?; if bit_depth >= 10 { + // An HDR (GNOME 50 portal) session never reaches this backend: its X2RGB10 frames ride + // the CPU/dmabuf paths (no CUDA import for the 10-bit formats yet), so the dispatcher + // opens the libav P010 path instead. Reaching here 10-bit means a CUDA capture payload + // on a 10-bit session — not wired; encode 8-bit rather than mislabel. tracing::warn!( - "Linux direct-NVENC: 10-bit requested but no P010 capture path exists yet \ - (Phase 5.1) — encoding 8-bit SDR" + "Linux direct-NVENC: 10-bit requested but the CUDA capture path has no 10-bit \ + import yet (HDR rides the libav P010 path) — encoding 8-bit SDR" ); } Ok(Self { diff --git a/crates/pf-encode/src/enc/linux/vaapi.rs b/crates/pf-encode/src/enc/linux/vaapi.rs index 4634cdca..add1017d 100644 --- a/crates/pf-encode/src/enc/linux/vaapi.rs +++ b/crates/pf-encode/src/enc/linux/vaapi.rs @@ -61,6 +61,10 @@ fn vaapi_sws_src(format: PixelFormat) -> Result { PixelFormat::Rgba => Pixel::RGBA, PixelFormat::Rgb => Pixel::RGB24, PixelFormat::Bgr => Pixel::BGR24, + // The GNOME 50+ HDR capture formats (PQ/BT.2020 packed 2:10:10:10) — the HDR CPU path's + // swscale source for the X2RGB10→P010 conversion. + PixelFormat::X2Rgb10 => Pixel::X2RGB10LE, + PixelFormat::X2Bgr10 => Pixel::X2BGR10LE, PixelFormat::Nv12 | PixelFormat::P010 | PixelFormat::Rgb10a2 | PixelFormat::Yuv444 => { bail!("VAAPI CPU-input path supports packed RGB/BGR only; got {format:?}") } @@ -101,6 +105,7 @@ fn low_power_override() -> Option { /// default on those kernels). AMD keeps its first-try full-feature open byte-for-byte unchanged. /// The resolved mode is cached per codec; `PUNKTFUNK_VAAPI_LOW_POWER` pins it. /// Safety contract is [`open_vaapi_encoder_mode`]'s (borrowed `device_ref`/`frames_ref`). +#[allow(clippy::too_many_arguments)] unsafe fn open_vaapi_encoder( codec: Codec, width: u32, @@ -109,6 +114,7 @@ unsafe fn open_vaapi_encoder( bitrate_bps: u64, device_ref: *mut ffi::AVBufferRef, frames_ref: *mut ffi::AVBufferRef, + ten_bit: bool, ) -> Result { let idx = lp_idx(codec); let modes: &[bool] = match low_power_override() { @@ -130,6 +136,7 @@ unsafe fn open_vaapi_encoder( bitrate_bps, device_ref, frames_ref, + ten_bit, lp, ) { Ok(enc) => { @@ -158,8 +165,9 @@ unsafe fn open_vaapi_encoder( } /// Build the FFmpeg encoder context (shared by both inner paths): name, mode, low-latency RC, -/// infinite GOP, BT.709-limited VUI, `pix_fmt=VAAPI`, and the given hw device + frames contexts. -/// Returns the opened encoder. `device_ref`/`frames_ref` are borrowed (ref'd into the context). +/// infinite GOP, the VUI (BT.709 limited SDR, or BT.2020 PQ limited for `ten_bit` HDR), +/// `pix_fmt=VAAPI`, and the given hw device + frames contexts. Returns the opened encoder. +/// `device_ref`/`frames_ref` are borrowed (ref'd into the context). #[allow(clippy::too_many_arguments)] unsafe fn open_vaapi_encoder_mode( codec: Codec, @@ -169,6 +177,7 @@ unsafe fn open_vaapi_encoder_mode( bitrate_bps: u64, device_ref: *mut ffi::AVBufferRef, frames_ref: *mut ffi::AVBufferRef, + ten_bit: bool, low_power: bool, ) -> Result { let name = codec.vaapi_name(); @@ -181,23 +190,39 @@ unsafe fn open_vaapi_encoder_mode( .context("alloc video encoder")?; video.set_width(width); video.set_height(height); - video.set_format(Pixel::NV12); // sw view; pix_fmt overridden to VAAPI below - // Fixed rate, CBR, no B-frames, ~1-frame VBV — the shared low-latency RC contract. + // sw view (pix_fmt overridden to VAAPI below): NV12, or P010 for the 10-bit HDR session. + video.set_format(if ten_bit { Pixel::P010LE } else { Pixel::NV12 }); + // Fixed rate, CBR, no B-frames, ~1-frame VBV — the shared low-latency RC contract. apply_low_latency_rc(&mut video, fps, bitrate_bps); let raw = video.as_mut_ptr(); (*raw).gop_size = i32::MAX; // no periodic IDR (forced-IDR via pict_type=I on RFI) - // We hand the encoder BT.709 *limited* NV12 (swscale CSC on the CPU path; scale_vaapi pinned - // to `out_color_matrix=bt709:out_range=limited` on the zero-copy path, with the full-range - // RGB input tagged), so signal that VUI — else the client decoder washes the picture out. - (*raw).colorspace = ffi::AVColorSpace::AVCOL_SPC_BT709; - (*raw).color_range = ffi::AVColorRange::AVCOL_RANGE_MPEG; - (*raw).color_primaries = ffi::AVColorPrimaries::AVCOL_PRI_BT709; - (*raw).color_trc = ffi::AVColorTransferCharacteristic::AVCOL_TRC_BT709; + if ten_bit { + // HDR10: BT.2020 primaries + SMPTE-2084 (PQ) transfer, limited range — matches the P010 + // the CSC produces (swscale BT.2020 on the CPU path; scale_vaapi pinned to bt2020 on the + // zero-copy path). The client decoder auto-detects PQ from the VUI. + (*raw).colorspace = ffi::AVColorSpace::AVCOL_SPC_BT2020_NCL; + (*raw).color_range = ffi::AVColorRange::AVCOL_RANGE_MPEG; + (*raw).color_primaries = ffi::AVColorPrimaries::AVCOL_PRI_BT2020; + (*raw).color_trc = ffi::AVColorTransferCharacteristic::AVCOL_TRC_SMPTE2084; + } else { + // We hand the encoder BT.709 *limited* NV12 (swscale CSC on the CPU path; scale_vaapi pinned + // to `out_color_matrix=bt709:out_range=limited` on the zero-copy path, with the full-range + // RGB input tagged), so signal that VUI — else the client decoder washes the picture out. + (*raw).colorspace = ffi::AVColorSpace::AVCOL_SPC_BT709; + (*raw).color_range = ffi::AVColorRange::AVCOL_RANGE_MPEG; + (*raw).color_primaries = ffi::AVColorPrimaries::AVCOL_PRI_BT709; + (*raw).color_trc = ffi::AVColorTransferCharacteristic::AVCOL_TRC_BT709; + } (*raw).pix_fmt = ffi::AVPixelFormat::AV_PIX_FMT_VAAPI; (*raw).hw_device_ctx = ffi::av_buffer_ref(device_ref); (*raw).hw_frames_ctx = ffi::av_buffer_ref(frames_ref); let mut opts = Dictionary::new(); + if ten_bit && codec == Codec::H265 { + // HEVC Main10. `hevc_vaapi` derives it from the P010 surfaces, but pin it explicitly so + // the depth is never silently dropped. (10-bit AV1 is input-driven — no profile knob.) + opts.set("profile", "main10"); + } // async_depth=1: `send_frame` blocks until THIS frame's ASIC encode completes — the lowest // latency structure libavcodec's vaapi_encode offers. Measured on the 780M at 1440p60: depth 1 // = 8.3 ms end-to-end p50 vs depth 2 = 18 ms, because with depth ≥ 2 frame N's packet only @@ -242,10 +267,59 @@ pub fn probe_can_encode(codec: Codec) -> bool { let prev = ffi::av_log_get_level(); ffi::av_log_set_level(ffi::AV_LOG_FATAL); let ok = match VaapiHw::new(ffi::AVPixelFormat::AV_PIX_FMT_NV12, 640, 480, 2) { - Ok(hw) => { - open_vaapi_encoder(codec, 640, 480, 30, 2_000_000, hw.device_ref, hw.frames_ref) - .is_ok() - } + Ok(hw) => open_vaapi_encoder( + codec, + 640, + 480, + 30, + 2_000_000, + hw.device_ref, + hw.frames_ref, + false, + ) + .is_ok(), + Err(_) => false, + }; + ffi::av_log_set_level(prev); + ok + } +} + +/// Probe whether the active VAAPI GPU can encode **10-bit** (HEVC Main10 / 10-bit AV1) from P010 +/// surfaces — the exact shape a live HDR session opens (P010 pool + Main10 profile + PQ VUI). The +/// driver rejects what the video engine can't do; the result is cached by the caller +/// ([`crate::can_encode_10bit`]), so a non-Main10 GPU resolves every session to 8-bit SDR before +/// the Welcome (honest downgrade). +pub fn probe_can_encode_10bit(codec: Codec) -> bool { + if !codec.supports_10bit() || codec == Codec::PyroWave { + return false; + } + if ffmpeg::init().is_err() { + return false; + } + // SAFETY: `ffmpeg::init()` returned Ok above, so libav is initialized. `av_log_{get,set}_level` + // only read/write libav's global integer log level (no pointer args). `VaapiHw::new` (an + // `unsafe fn`) builds a VAAPI device + P010 frames pool from the literal args and hands back a + // RAII handle; `open_vaapi_encoder` (an `unsafe fn`) borrows `hw.device_ref`/`hw.frames_ref` — + // the two non-null refs `VaapiHw::new` just created, live locals for the whole match arm — and + // `av_buffer_ref`s them into the probe encoder. Both `hw` and the encoder drop (RAII) at arm end. + unsafe { + // A missing VA device / no Main10 entrypoint is an expected probe outcome — quiet ffmpeg's + // error for the probe, then restore the level. + let prev = ffi::av_log_get_level(); + ffi::av_log_set_level(ffi::AV_LOG_FATAL); + let ok = match VaapiHw::new(ffi::AVPixelFormat::AV_PIX_FMT_P010LE, 640, 480, 2) { + Ok(hw) => open_vaapi_encoder( + codec, + 640, + 480, + 30, + 2_000_000, + hw.device_ref, + hw.frames_ref, + true, + ) + .is_ok(), Err(_) => false, }; ffi::av_log_set_level(prev); @@ -348,12 +422,21 @@ impl CpuInner { bitrate_bps: u64, ) -> Result { let src_pixel = vaapi_sws_src(format)?; + // A 10-bit HDR capture (X2RGB10/X2BGR10, PQ/BT.2020) uploads P010 and encodes Main10; the + // 8-bit paths keep NV12/BT.709 byte-for-byte unchanged. + let ten_bit = format.is_hdr_rgb10(); + let staging_av = if ten_bit { + ffi::AVPixelFormat::AV_PIX_FMT_P010LE + } else { + ffi::AVPixelFormat::AV_PIX_FMT_NV12 + }; const POOL: c_int = 16; // SAFETY: `VaapiHw::new` (an `unsafe fn`) requires libav initialized — guaranteed because the // only path here is `VaapiEncoder::open` → `ensure_inner` → `CpuInner::open`, and `open` ran - // `ffmpeg::init()`. The args are valid: NV12 sw_format, the validated positive `width`/`height`, - // pool=16. It returns a RAII `VaapiHw` that unrefs its two `AVBufferRef`s on drop. - let hw = unsafe { VaapiHw::new(ffi::AVPixelFormat::AV_PIX_FMT_NV12, width, height, POOL)? }; + // `ffmpeg::init()`. The args are valid: an NV12/P010 sw_format, the validated positive + // `width`/`height`, pool=16. It returns a RAII `VaapiHw` that unrefs its two `AVBufferRef`s + // on drop. + let hw = unsafe { VaapiHw::new(staging_av, width, height, POOL)? }; // SAFETY: `open_vaapi_encoder` (an `unsafe fn`) borrows `hw.device_ref`/`hw.frames_ref` — both // non-null (`VaapiHw::new` guarantees it) and from the `hw` just built above, which is a live // local that outlives this synchronous call. The fn `av_buffer_ref`s them into the encoder, so @@ -368,16 +451,19 @@ impl CpuInner { bitrate_bps, hw.device_ref, hw.frames_ref, + ten_bit, )? }; - // swscale RGB→NV12, BT.709 limited (matches the VUI), no rescale. + // swscale RGB→NV12 (BT.709 limited) or X2RGB10→P010 (BT.2020 limited, HDR) — matches the + // VUI; no rescale. let src_av = pixel_to_av(src_pixel); // SAFETY: `sws_getContext` allocates a swscale context for the given src/dst dimensions and // pixel formats. All four dims are the encoder's positive `width`/`height` cast to `c_int`; // `src_av` is a valid `AVPixelFormat` (from `pixel_to_av` of the `vaapi_sws_src`-validated - // `src_pixel`), the dst is NV12. The three trailing pointers (srcFilter, dstFilter, param) are - // explicitly null = "use defaults", which the API documents as accepted. No Rust memory is - // borrowed — only by-value ints/enums — and the returned pointer is null-checked just below. + // `src_pixel`), the dst is NV12/P010. The three trailing pointers (srcFilter, dstFilter, + // param) are explicitly null = "use defaults", which the API documents as accepted. No Rust + // memory is borrowed — only by-value ints/enums — and the returned pointer is null-checked + // just below. let sws = unsafe { ffi::sws_getContext( width as c_int, @@ -385,7 +471,7 @@ impl CpuInner { src_av, width as c_int, height as c_int, - ffi::AVPixelFormat::AV_PIX_FMT_NV12, + staging_av, SWS_POINT, ptr::null_mut(), ptr::null_mut(), @@ -393,45 +479,51 @@ impl CpuInner { ) }; if sws.is_null() { - bail!("sws_getContext(RGB→NV12) failed"); + bail!("sws_getContext(RGB→{})", if ten_bit { "P010" } else { "NV12" }); } // SAFETY: `sws` is the non-null `SwsContext` from `sws_getContext` above (the `is_null()` - // check immediately preceding returned false). `sws_getCoefficients(SWS_CS_ITU709)` returns a - // pointer into a libswscale static const coefficient table valid for the whole process, reused - // here for both the inverse (src) and forward (dst) matrices. `sws_setColorspaceDetails` only - // reads those tables and writes scalar CSC settings into `sws`; the table pointer outlives the - // synchronous call and no Rust memory is passed. + // check immediately preceding returned false). The coefficient table from + // `sws_getCoefficients` (ITU-709, or BT.2020 NCL for the HDR path — matching the VUI) is a + // libswscale static const valid for the whole process, reused here for both the inverse + // (src) and forward (dst) matrices. `sws_setColorspaceDetails` only reads those tables and + // writes scalar CSC settings into `sws`; the table pointer outlives the synchronous call and + // no Rust memory is passed. unsafe { - let cs709 = ffi::sws_getCoefficients(SWS_CS_ITU709); - ffi::sws_setColorspaceDetails(sws, cs709, 1, cs709, 0, 0, 1 << 16, 1 << 16); + let cs = ffi::sws_getCoefficients(if ten_bit { + super::libav::SWS_CS_BT2020 + } else { + SWS_CS_ITU709 + }); + ffi::sws_setColorspaceDetails(sws, cs, 1, cs, 0, 0, 1 << 16, 1 << 16); } // SAFETY: `av_frame_alloc` returns a fresh, uniquely-owned heap `AVFrame` (null-checked — on // null we free the already-built `sws` and bail). We then write the plain `format`/`width`/ // `height` fields through the non-null, properly-aligned `f` (sole owner, not yet shared). // `av_frame_get_buffer(f, 0)` allocates backing storage for those dims/format; on failure we // free `f` and `sws` (unwinding the half-built state) and bail. On success `f` is a fully-owned - // NV12 frame stored in `CpuInner.nv12` and freed once in `CpuInner::drop`. `f` is a unique - // fresh pointer, so none of these writes alias anything. + // NV12/P010 frame stored in `CpuInner.nv12` and freed once in `CpuInner::drop`. `f` is a + // unique fresh pointer, so none of these writes alias anything. let nv12 = unsafe { let f = ffi::av_frame_alloc(); if f.is_null() { ffi::sws_freeContext(sws); - bail!("av_frame_alloc(NV12) failed"); + bail!("av_frame_alloc(staging) failed"); } - (*f).format = ffi::AVPixelFormat::AV_PIX_FMT_NV12 as c_int; + (*f).format = staging_av as c_int; (*f).width = width as c_int; (*f).height = height as c_int; if ffi::av_frame_get_buffer(f, 0) < 0 { let mut f = f; ffi::av_frame_free(&mut f); ffi::sws_freeContext(sws); - bail!("av_frame_get_buffer(NV12) failed"); + bail!("av_frame_get_buffer(staging) failed"); } f }; tracing::info!( encoder = codec.vaapi_name(), - "VAAPI encode active ({width}x{height}@{fps}, CPU→NV12 upload path)" + "VAAPI encode active ({width}x{height}@{fps}, CPU→{} upload path)", + if ten_bit { "P010 (HDR10)" } else { "NV12" } ); Ok(CpuInner { enc, @@ -563,6 +655,15 @@ impl DmabufInner { ) -> Result { let drm_fourcc = pf_frame::drm_fourcc(format) .ok_or_else(|| anyhow!("no DRM fourcc for {format:?} (VAAPI zero-copy)"))?; + // A 10-bit HDR capture (X2RGB10/X2BGR10 dmabufs, PQ/BT.2020) maps + CSCs to P010 and + // encodes Main10; the 8-bit paths keep the NV12/BT.709 graph byte-for-byte unchanged. + let ten_bit = format.is_hdr_rgb10(); + let sw_format = match format { + PixelFormat::X2Rgb10 => ffi::AVPixelFormat::AV_PIX_FMT_X2RGB10LE, + PixelFormat::X2Bgr10 => ffi::AVPixelFormat::AV_PIX_FMT_X2BGR10LE, + // The 8-bit capture formats are all XR24-shaped packed RGB (the historical BGR0 view). + _ => ffi::AVPixelFormat::AV_PIX_FMT_BGR0, + }; let node = render_node(); // SAFETY: libav is initialized (`VaapiEncoder::open` ran `ffmpeg::init()` before // `ensure_inner` → `DmabufInner::open`). Every raw pointer dereferenced below is either freshly @@ -628,7 +729,7 @@ impl DmabufInner { } let fc = (*drm_frames).data as *mut ffi::AVHWFramesContext; (*fc).format = ffi::AVPixelFormat::AV_PIX_FMT_DRM_PRIME; - (*fc).sw_format = ffi::AVPixelFormat::AV_PIX_FMT_BGR0; // packed XR24 RGB plane + (*fc).sw_format = sw_format; // packed XR24 RGB plane, or XR30/XB30 for HDR (*fc).width = width as c_int; (*fc).height = height as c_int; if ffi::av_hwframe_ctx_init(drm_frames) < 0 { @@ -715,14 +816,24 @@ impl DmabufInner { } init!(src, ptr::null(), "buffer"); init!(hwmap, c"mode=read".as_ptr(), "hwmap"); - // Pin the VPP's output colour to what the encoder's VUI signals (BT.709 limited). - // Without the explicit options the conversion matrix is whatever the driver defaults - // to for an unspecified output (Mesa: BT.601) — a hue shift against the signaled VUI. - init!( - scale, - c"format=nv12:out_color_matrix=bt709:out_range=limited".as_ptr(), - "scale_vaapi" - ); + // Pin the VPP's output colour to what the encoder's VUI signals (BT.709 limited SDR, + // or BT.2020 limited P010 for HDR — the PQ transfer is per-channel and rides through + // the matrix untouched). Without the explicit options the conversion matrix is + // whatever the driver defaults to for an unspecified output (Mesa: BT.601) — a hue + // shift against the signaled VUI. + if ten_bit { + init!( + scale, + c"format=p010:out_color_matrix=bt2020:out_range=limited".as_ptr(), + "scale_vaapi" + ); + } else { + init!( + scale, + c"format=nv12:out_color_matrix=bt709:out_range=limited".as_ptr(), + "scale_vaapi" + ); + } init!(sink, ptr::null(), "buffersink"); let link = |a: *mut ffi::AVFilterContext, b: *mut ffi::AVFilterContext| -> c_int { @@ -766,6 +877,7 @@ impl DmabufInner { bitrate_bps, vaapi_device, nv12_ctx, + ten_bit, ) { Ok(enc) => enc, Err(e) => { @@ -779,7 +891,8 @@ impl DmabufInner { tracing::info!( encoder = codec.vaapi_name(), - "VAAPI encode active ({width}x{height}@{fps}, zero-copy dmabuf → GPU NV12)" + "VAAPI encode active ({width}x{height}@{fps}, zero-copy dmabuf → GPU {})", + if ten_bit { "P010 (HDR10)" } else { "NV12" } ); Ok(DmabufInner { enc, @@ -987,8 +1100,22 @@ impl VaapiEncoder { bit_depth: u8, chroma: super::ChromaFormat, ) -> Result { - if bit_depth != 8 { - tracing::warn!(bit_depth, "VAAPI 10-bit not yet wired — encoding 8-bit"); + // 10-bit rides on the captured format: an HDR capture (X2RGB10/X2BGR10) opens the P010 / + // Main10 / PQ-VUI variant of whichever inner path the first frame selects. A 10-bit + // request whose capture stayed SDR honestly encodes 8-bit; the reverse (PQ frames on an + // 8-bit session) is refused so PQ content is never mislabeled BT.709. + if format.is_hdr_rgb10() && bit_depth != 10 { + bail!( + "captured 10-bit HDR frames ({format:?}) on an {bit_depth}-bit VAAPI session — \ + refusing to mislabel PQ content" + ); + } + if bit_depth == 10 && !format.is_hdr_rgb10() { + tracing::warn!( + bit_depth, + ?format, + "10-bit requested but the capture stayed SDR — encoding 8-bit" + ); } // VAAPI 4:4:4 is deferred (see `probe_can_encode_444`): no validated AMD/Intel hardware in the // lab exposes a HEVC 4:4:4 encode entrypoint, and the probe returns false so the host never diff --git a/crates/pf-encode/src/enc/sw.rs b/crates/pf-encode/src/enc/sw.rs index df056192..3a6b04e4 100644 --- a/crates/pf-encode/src/enc/sw.rs +++ b/crates/pf-encode/src/enc/sw.rs @@ -181,10 +181,10 @@ impl Encoder for OpenH264Encoder { PixelFormat::Bgr => (3, 2, 1, 0), PixelFormat::Rgba | PixelFormat::Rgbx => (4, 0, 1, 2), PixelFormat::Bgra | PixelFormat::Bgrx => (4, 2, 1, 0), - // 10-bit HDR comes only from the GPU NVENC path; the software 8-bit H.264 encoder - // can't represent it (and never receives it — the capturer pairs Rgb10a2 with NVENC). - PixelFormat::Rgb10a2 => { - anyhow::bail!("software H.264 encoder cannot encode 10-bit HDR (Rgb10a2)") + // 10-bit HDR comes only from the GPU paths; the software 8-bit H.264 encoder can't + // represent it (and never receives it — HDR is never negotiated on a software host). + PixelFormat::Rgb10a2 | PixelFormat::X2Rgb10 | PixelFormat::X2Bgr10 => { + anyhow::bail!("software H.264 encoder cannot encode 10-bit HDR ({:?})", self.src_format) } // NV12/P010 are GPU-resident video-processor outputs for the NVENC path; the software // encoder never receives them (it only gets CPU RGB frames). diff --git a/crates/pf-encode/src/lib.rs b/crates/pf-encode/src/lib.rs index 5ea0db64..6fde1365 100644 --- a/crates/pf-encode/src/lib.rs +++ b/crates/pf-encode/src/lib.rs @@ -288,8 +288,14 @@ fn open_video_backend( // stream never dies over the new path. `format`/`bit_depth`/`chroma` only matter to VAAPI — // the Vulkan backend imports the dmabuf and does its own 8-bit 4:2:0 CSC. let open_amd_intel = || -> Result<(Box, &'static str)> { + // An HDR session (10-bit + a PQ/BT.2020 capture format) must skip the Vulkan Video + // backend — it hardcodes an 8-bit 4:2:0 BT.709 CSC — and take the libav VAAPI path, + // which has the P010/Main10/PQ wiring. SDR sessions keep the Vulkan default. #[cfg(feature = "vulkan-encode")] - if matches!(codec, Codec::H265 | Codec::Av1) && vulkan_encode_enabled() { + if matches!(codec, Codec::H265 | Codec::Av1) + && vulkan_encode_enabled() + && !(bit_depth == 10 && format.is_hdr_rgb10()) + { match vulkan_video::VulkanVideoEncoder::open(codec, width, height, fps, bitrate_bps) { Ok(e) => { @@ -956,11 +962,10 @@ pub fn can_encode_444(_codec: Codec) -> bool { /// Backend truth: Windows **NVENC** queries the per-codec `NV_ENC_CAPS_SUPPORT_10BIT_ENCODE` cap; /// native **AMF** `Init`s a tiny P010 encoder with the 10-bit profile props (the driver rejects /// what the VCN can't do). **QSV** stays `false` until validated on Intel glass — the libavcodec -/// Main10 incantation can silently encode 8-bit, the same stance as its 4:4:4 probe. Every -/// **Linux** backend is `false` today: direct-NVENC/CUDA pins 8-bit until a P010 capture path -/// exists (Phase 5.1), libav `hevc_nvenc` needs a 10-bit input format the capturer never feeds, -/// VAAPI 10-bit isn't wired, and Vulkan-video hardcodes 8-bit — so Linux hosts honestly negotiate -/// 8-bit SDR. +/// Main10 incantation can silently encode 8-bit, the same stance as its 4:4:4 probe. **Linux** +/// probes a tiny real Main10 open on the auto-resolved backend — libav NVENC (the HDR X2RGB10→ +/// P010 swscale path) or VAAPI (P010 pool + Main10) — for the GNOME 50+ HDR portal capture; +/// the direct-SDK CUDA path and Vulkan-video stay 8-bit and a 10-bit session routes around them. #[cfg(any(target_os = "linux", target_os = "windows"))] pub fn can_encode_10bit(codec: Codec) -> bool { use std::collections::HashMap; @@ -985,8 +990,18 @@ pub fn can_encode_10bit(codec: Codec) -> bool { let supported = { #[cfg(target_os = "linux")] { - // No Linux backend encodes 10-bit yet (see the fn doc) — never negotiate it. - false + // NVENC (libav, the HDR P010 swscale path) or VAAPI (P010 upload / dmabuf graph), + // probed by opening a tiny real Main10 encoder — the same honesty contract as + // `can_encode_444`. Vulkan-video and the direct-SDK CUDA path stay 8-bit; a 10-bit + // session routes around them (see `open_video_backend`). NOTE: encode capability is + // only half the Linux gate — the capture side (GNOME 50+ portal monitor in HDR mode) + // is resolved separately by the host (`capturer_supports_hdr` / the GameStream RTSP + // honor), since this probe can't know what the compositor will negotiate. + if linux_auto_is_vaapi() { + vaapi::probe_can_encode_10bit(codec) + } else { + linux::probe_can_encode_10bit(codec) + } } #[cfg(target_os = "windows")] { diff --git a/crates/pf-frame/src/lib.rs b/crates/pf-frame/src/lib.rs index 4e0274b4..1eda307b 100644 --- a/crates/pf-frame/src/lib.rs +++ b/crates/pf-frame/src/lib.rs @@ -56,6 +56,19 @@ pub enum PixelFormat { /// `DeviceBuffer::yuv444` — three full-res planes stacked in one allocation); NVENC encodes /// it natively under the Range-Extensions profile. Never a CPU payload. Yuv444, + /// 10-bit RGB packed `x:R:G:B 2:10:10:10` little-endian (SPA `xRGB_210LE`, DRM `XRGB2101010` / + /// `XR30`, ffmpeg `x2rgb10le`, NVENC `ARGB10`) — as an LE u32: B in bits 0-9, G 10-19, R 20-29. + /// The Linux GNOME 50+ HDR screencast source format: Mutter advertises it (with BT.2020 + /// primaries + SMPTE ST.2084 PQ transfer) for a monitor in HDR mode, so the samples are + /// PQ-encoded BT.2020 RGB. Linux-only; the Windows HDR path stays `Rgb10a2`/`P010`. + X2Rgb10, + /// 10-bit RGB packed `x:B:G:R 2:10:10:10` little-endian (SPA `xBGR_210LE`, DRM `XBGR2101010` / + /// `XB30`, ffmpeg `x2bgr10le`, NVENC `ABGR10`) — as an LE u32: R in bits 0-9, G 10-19, B 20-29; + /// the same memory layout as the Windows [`Rgb10a2`](Self::Rgb10a2) (DXGI `R10G10B10A2`). The + /// second GNOME 50+ HDR screencast format (same PQ/BT.2020 colorimetry as + /// [`X2Rgb10`](Self::X2Rgb10)); kept separate from `Rgb10a2` so the Linux and Windows HDR + /// paths stay independently greppable. + X2Bgr10, } impl PixelFormat { @@ -67,6 +80,12 @@ impl PixelFormat { _ => 4, } } + + /// True for the packed 10-bit RGB layouts a Linux HDR (BT.2020 PQ) capture negotiates — + /// the formats that make a session's encode bit depth 10 (HEVC Main10 / 10-bit AV1). + pub fn is_hdr_rgb10(self) -> bool { + matches!(self, PixelFormat::X2Rgb10 | PixelFormat::X2Bgr10) + } } /// DRM FourCC for a packed 32-bit format name (little-endian, e.g. `b"XR24"`). @@ -86,6 +105,9 @@ pub fn drm_fourcc(format: PixelFormat) -> Option { Bgra => drm_fourcc_code(b"AR24"), // DRM_FORMAT_ARGB8888 Rgbx => drm_fourcc_code(b"XB24"), // DRM_FORMAT_XBGR8888 Rgba => drm_fourcc_code(b"AB24"), // DRM_FORMAT_ABGR8888 + // The GNOME 50+ HDR screencast formats (packed 2:10:10:10, PQ/BT.2020). + X2Rgb10 => drm_fourcc_code(b"XR30"), // DRM_FORMAT_XRGB2101010 + X2Bgr10 => drm_fourcc_code(b"XB30"), // DRM_FORMAT_XBGR2101010 // 24-bit packed RGB/BGR have no straightforward dmabuf import here; use the CPU path. // Rgb10a2/Nv12/P010 are the Windows HDR / video-processor formats — never produced on // Linux; Yuv444 is OUR convert's OUTPUT, never a capture source format. diff --git a/crates/punktfunk-host/src/capture.rs b/crates/punktfunk-host/src/capture.rs index af9e6d54..2a6ca074 100644 --- a/crates/punktfunk-host/src/capture.rs +++ b/crates/punktfunk-host/src/capture.rs @@ -12,7 +12,10 @@ use anyhow::Result; // `crate::capture::*` (the capture mechanics that used the rest moved into pf-capture). pub use pf_frame::{CapturedFrame, OutputFormat, PixelFormat}; // The capturer types + trait + synthetics live in `pf-capture`; re-export them at the old paths. -pub use pf_capture::{capturer_supports_444, Capturer, FastSyntheticCapturer, SyntheticCapturer}; +pub use pf_capture::{ + capturer_supports_444, capturer_supports_hdr, Capturer, FastSyntheticCapturer, + SyntheticCapturer, +}; // `crate::capture::dxgi::{install_gpu_pref_hook, hdr_p010_selftest}` (main.rs subcommands) and // `crate::capture::synthetic_nv12` resolve through pf-capture's Windows modules. #[cfg(target_os = "windows")] @@ -45,18 +48,20 @@ fn zero_copy_policy() -> pf_capture::ZeroCopyPolicy { } } -/// Open a live capturer for a client-sized monitor via the xdg ScreenCast portal. +/// Open a live capturer for a client-sized monitor via the xdg ScreenCast portal. `want_hdr` +/// offers the GNOME 50+ 10-bit PQ/BT.2020 formats (pass it only when the session negotiated HDR +/// AND the mirrored monitor is in HDR mode — see [`pf_capture::gnome_hdr_monitor_active`]). #[cfg(target_os = "linux")] -pub fn open_portal_monitor() -> Result> { +pub fn open_portal_monitor(want_hdr: bool) -> Result> { // On RemoteDesktop-capable desktops (KWin/GNOME) anchor ScreenCast to a RemoteDesktop // session so it inherits that grant headlessly; wlroots/Sway has no RemoteDesktop portal, // so use a plain ScreenCast session there. let anchored = crate::inject::default_backend() == crate::inject::Backend::Libei; - pf_capture::open_portal_monitor(anchored, zero_copy_policy()) + pf_capture::open_portal_monitor(anchored, want_hdr, zero_copy_policy()) } #[cfg(not(target_os = "linux"))] -pub fn open_portal_monitor() -> Result> { +pub fn open_portal_monitor(_want_hdr: bool) -> Result> { anyhow::bail!("portal capture requires Linux (xdg-desktop-portal + PipeWire)") } @@ -69,11 +74,13 @@ pub fn capture_virtual_output( want: OutputFormat, _capture: crate::session_plan::CaptureBackend, ) -> Result> { - // The Linux host stays 8-bit (HDR is blocked upstream) and the portal negotiates its own pixel - // format, so `want.gpu` gates GPU zero-copy capture (the capture backend is always the portal — - // the `CaptureBackend` arg is a Windows-only dispatch) and `want.chroma_444` selects the - // worker's planar-YUV444 GPU convert. `gpu = false` (4:4:4 without zero-copy) forces the CPU - // mmap path so the encoder gets CPU-resident RGB to swscale into YUV444P. + // The Linux NATIVE plane stays 8-bit (Mutter's virtual-monitor streams are SDR-only upstream; + // the GNOME 50+ HDR path is monitor-mirror only — `open_portal_monitor`) and the portal + // negotiates its own pixel format, so `want.gpu` gates GPU zero-copy capture (the capture + // backend is always the portal — the `CaptureBackend` arg is a Windows-only dispatch) and + // `want.chroma_444` selects the worker's planar-YUV444 GPU convert. `gpu = false` (4:4:4 + // without zero-copy) forces the CPU mmap path so the encoder gets CPU-resident RGB to swscale + // into YUV444P. pf_capture::open_virtual_output( vout.remote_fd, vout.node_id, diff --git a/crates/punktfunk-host/src/gamestream/mod.rs b/crates/punktfunk-host/src/gamestream/mod.rs index 1ba86747..87539d6b 100644 --- a/crates/punktfunk-host/src/gamestream/mod.rs +++ b/crates/punktfunk-host/src/gamestream/mod.rs @@ -50,21 +50,45 @@ pub const SCM_AV1_MAIN10: u32 = 0x0002_0000; /// The **SDR baseline** codec mask: H.264, HEVC Main, AV1 Main 8-bit (= 65793). HEVC Main10 (HDR) is /// layered on top of this at runtime by `serverinfo::codec_mode_support` when — and only when — the /// host can actually deliver it ([`host_hdr_capable`]); it is never a static claim, because a non-HDR -/// host (Linux, or a Windows host without the `PUNKTFUNK_10BIT` opt-in) must not invite a client into -/// an HDR mode it can't produce. (The previous placeholder 3843 = 0xF03 wrongly claimed HEVC Main10 + +/// host (a host without the `PUNKTFUNK_10BIT` opt-in, or a Linux host whose video source / encoder +/// can't do Main10) must not invite a client into an HDR mode it can't produce. (The previous placeholder 3843 = 0xF03 wrongly claimed HEVC Main10 + /// 4:4:4 and *no* AV1.) 4:4:4 stays off entirely on GameStream: stock Moonlight is 4:2:0 — /// full-chroma is a punktfunk/1-native negotiation only (`crate::capture::capturer_supports_444`). pub const SERVER_CODEC_MODE_SUPPORT: u32 = SCM_H264 | SCM_HEVC | SCM_AV1_MAIN8; /// Whether this host can deliver an **HDR** (HEVC Main10 / BT.2020 PQ) GameStream — the single gate -/// for advertising [`SCM_HEVC_MAIN10`] in serverinfo and `IsHdrSupported` per app, and for honoring a -/// client's `dynamicRangeMode` request. HDR capture+encode is **Windows-only** (the Linux host is -/// 8-bit, blocked upstream) and behind the operator's `PUNKTFUNK_10BIT` opt-in — the same policy gate -/// the native punktfunk/1 plane honors. When this is true the IDD-push capturer streams HEVC Main10 PQ -/// whenever the desktop is HDR, and a client HDR request makes the GameStream video path proactively -/// enable advanced color on the per-session virtual display so PQ flows even from an SDR desktop. +/// for advertising [`SCM_HEVC_MAIN10`] in serverinfo and `IsHdrSupported` per app, and (together +/// with the live capture-side check at RTSP time) for honoring a client's `dynamicRangeMode` +/// request. Behind the operator's `PUNKTFUNK_10BIT` opt-in — the same policy gate the native +/// punktfunk/1 plane honors — on both OSes. +/// +/// **Windows**: the IDD-push capturer streams HEVC Main10 PQ whenever the desktop is HDR, and a +/// client HDR request proactively enables advanced color on the per-session virtual display so PQ +/// flows even from an SDR desktop. +/// +/// **Linux**: the GNOME 50+ portal **monitor mirror** (`video_source=portal`) can negotiate the +/// 10-bit PQ formats while the mirrored monitor is in HDR mode, and the NVENC/VAAPI encoders have +/// a probed Main10 path ([`crate::encode::can_encode_10bit`]). The virtual-output source stays SDR +/// (Mutter's RecordVirtual streams are 8-bit-only upstream), so this is `false` for it. Whether +/// the monitor is ACTUALLY in HDR mode right now is checked live at RTSP honor time +/// ([`pf_capture::gnome_hdr_monitor_active`]) — this fn is the static serverinfo capability. pub fn host_hdr_capable() -> bool { - cfg!(target_os = "windows") && pf_host_config::config().ten_bit + if !pf_host_config::config().ten_bit { + return false; + } + #[cfg(target_os = "windows")] + { + true + } + #[cfg(target_os = "linux")] + { + pf_host_config::config().video_source.as_deref() == Some("portal") + && crate::encode::can_encode_10bit(crate::encode::Codec::H265) + } + #[cfg(not(any(target_os = "windows", target_os = "linux")))] + { + false + } } /// Stable host identity + advertised capabilities, shared across control-plane handlers. @@ -141,8 +165,11 @@ pub struct AppState { pub rfi_range: std::sync::Arc>>, /// Persistent screen capturer, reused across streams so reconnects don't spawn a second /// (conflicting) screencast session. The video thread borrows it for the stream's duration - /// and returns it; `set_active` gates its cost while idle. - pub video_cap: std::sync::Arc>>>, + /// and returns it; `set_active` gates its cost while idle. The slot's `bool` records whether + /// it was opened with the HDR (10-bit PQ) offer — a stream whose negotiated `hdr` differs + /// drops the pooled capturer and opens a fresh screencast session at the right depth + /// (mirroring the audio capturer's channel-count reuse gate). + pub video_cap: stream::CapturerSlot, /// Persistent audio capturer, reused across streams when the channel count still matches /// (avoids a PipeWire stream setup per reconnect); drained on reuse so no stale audio is /// sent, dropped + reopened when a session negotiates a different channel count. diff --git a/crates/punktfunk-host/src/gamestream/rtsp.rs b/crates/punktfunk-host/src/gamestream/rtsp.rs index 766871dc..ad1b4cdf 100644 --- a/crates/punktfunk-host/src/gamestream/rtsp.rs +++ b/crates/punktfunk-host/src/gamestream/rtsp.rs @@ -396,18 +396,30 @@ fn stream_config(map: &HashMap) -> Option { _ => Codec::H264, }; // 10-bit/HDR request (Moonlight sets `dynamicRangeMode != 0` only when it both saw our Main10 SCM - // bit AND the user enabled HDR). Honor it only when the host can actually deliver Main10 (Windows + - // PUNKTFUNK_10BIT, `host_hdr_capable`); when honored, the video path proactively enables advanced - // color on the virtual display so a PQ stream flows even from an SDR desktop. A request we can't - // honor degrades to 8-bit SDR (and a desktop that is ALREADY HDR still streams PQ regardless, since - // the IDD-push capturer follows the display). + // bit AND the user enabled HDR). Honor it only when the host can actually deliver Main10 + // (`host_hdr_capable` — Windows IDD-push, or the Linux GNOME 50+ portal mirror). On Windows, + // when honored, the video path proactively enables advanced color on the virtual display so a + // PQ stream flows even from an SDR desktop. On Linux the portal can only deliver PQ while the + // MIRRORED monitor is in HDR mode, so additionally probe the live colour mode here (one D-Bus + // round-trip, sync RTSP thread) — an SDR desktop honestly degrades to 8-bit SDR up front + // instead of running the capture negotiation into its timeout. A request we can't honor + // degrades to 8-bit SDR (and a Windows desktop that is ALREADY HDR still streams PQ + // regardless, since the IDD-push capturer follows the display). let hdr_requested = parse_u("x-nv-video[0].dynamicRangeMode").unwrap_or(0) != 0; - let hdr = hdr_requested && crate::gamestream::host_hdr_capable(); + let mut hdr = hdr_requested && crate::gamestream::host_hdr_capable(); if hdr_requested && !hdr { tracing::warn!( "client requested HDR (dynamicRangeMode != 0) but host is not HDR-capable — streaming 8-bit SDR" ); } + #[cfg(target_os = "linux")] + if hdr && !pf_capture::gnome_hdr_monitor_active() { + tracing::warn!( + "client requested HDR but no monitor is in BT.2100 (HDR) colour mode — enable HDR in \ + GNOME Settings → Displays (GNOME 50+) to stream it; streaming 8-bit SDR" + ); + hdr = false; + } // The client's requested CSC (moonlight-common-c SdpGenerator.c: `encoderCscMode = // (colorspace << 1) | fullRange` — colorspace 0=Rec601, 1=Rec709, 2=Rec2020). Moonlight // renderers configure their YUV→RGB from this REQUESTED value (not the bitstream VUI), so a diff --git a/crates/punktfunk-host/src/gamestream/stream.rs b/crates/punktfunk-host/src/gamestream/stream.rs index 0a15b979..551b72c6 100644 --- a/crates/punktfunk-host/src/gamestream/stream.rs +++ b/crates/punktfunk-host/src/gamestream/stream.rs @@ -34,8 +34,9 @@ pub struct StreamConfig { } /// Slot for the persistent screen capturer, shared with the control plane and reused across -/// streams so a reconnect doesn't open a second (conflicting) screencast session. -pub type CapturerSlot = Arc>>>; +/// streams so a reconnect doesn't open a second (conflicting) screencast session. The `bool` is +/// the pooled capturer's HDR-ness (see `AppState::video_cap`). +pub type CapturerSlot = Arc, bool)>>>; /// A pending client reference-frame-invalidation range (lost `firstFrame..=lastFrame`), set by the /// control plane and drained by the video thread (see [`AppState::rfi_range`](super::AppState)). @@ -120,7 +121,7 @@ fn run( running: &Arc, force_idr: &AtomicBool, rfi_range: &std::sync::Mutex>, - video_cap: &std::sync::Mutex>>, + video_cap: &std::sync::Mutex, bool)>>, // Shared stats recorder for the web-console capture/graph. Threaded into `stream_body` (the // encode loop); per-frame sample emission is wired by a later pass. stats: &Arc, @@ -243,15 +244,31 @@ fn run( } // Reuse the persistent capturer (one screencast session → clean reconnect); create it on - // the first stream. Borrow it for this stream and return it on exit. - let mut capturer: Box = match video_cap.lock().unwrap().take() { + // the first stream. Borrow it for this stream and return it on exit. Reuse is gated on the + // pooled capturer's HDR-ness matching this stream's negotiated `cfg.hdr` — the depth is a + // PipeWire-negotiation-time property of the screencast session, so an HDR↔SDR change needs a + // fresh session (same pattern as the audio capturer's channel-count gate). + let pooled = match video_cap.lock().unwrap().take() { + Some((c, was_hdr)) if was_hdr == cfg.hdr => Some(c), + Some((c, was_hdr)) => { + tracing::info!( + was_hdr, + want_hdr = cfg.hdr, + "video source: pooled capturer depth mismatch — opening a fresh screencast session" + ); + drop(c); + None + } + None => None, + }; + let mut capturer: Box = match pooled { Some(c) => { tracing::info!("video source: reusing capturer"); c } None if pf_host_config::config().video_source.as_deref() == Some("portal") => { - tracing::info!("video source: portal desktop capture"); - capture::open_portal_monitor().context("open portal capturer")? + tracing::info!(hdr = cfg.hdr, "video source: portal desktop capture"); + capture::open_portal_monitor(cfg.hdr).context("open portal capturer")? } None => { tracing::info!("video source: synthetic test pattern"); @@ -272,7 +289,7 @@ fn run( &client_label, ); capturer.set_active(false); - *video_cap.lock().unwrap() = Some(capturer); + *video_cap.lock().unwrap() = Some((capturer, cfg.hdr)); result } @@ -380,7 +397,9 @@ fn open_gs_virtual_source( // HDR: pass the negotiated `cfg.hdr` (client asked for HDR AND the host can deliver it). On the // Windows IDD-push path this proactively enables advanced color on the virtual display so a Main10 // PQ stream flows even from an SDR desktop; an already-HDR desktop streams PQ regardless (the - // capturer follows the display). No-op on Linux (8-bit, and `cfg.hdr` is always false there). + // capturer follows the display). No-op on Linux: virtual-output capture is SDR-only upstream + // (Mutter RecordVirtual), and `host_hdr_capable` therefore keeps `cfg.hdr` false for this + // source — the Linux HDR path is the portal monitor mirror (`video_source=portal`). let capturer = capture::capture_virtual_output( vout, capture::OutputFormat::resolve(cfg.hdr, crate::encode::resolved_backend_is_gpu()), @@ -399,7 +418,11 @@ fn open_gs_virtual_source( fn gs_bit_depth(format: crate::capture::PixelFormat) -> u8 { use crate::capture::PixelFormat; match format { - PixelFormat::P010 | PixelFormat::Rgb10a2 => 10, + // Windows IDD-push HDR formats, and the Linux GNOME 50+ portal HDR formats. + PixelFormat::P010 + | PixelFormat::Rgb10a2 + | PixelFormat::X2Rgb10 + | PixelFormat::X2Bgr10 => 10, _ => 8, } } diff --git a/crates/punktfunk-host/src/main.rs b/crates/punktfunk-host/src/main.rs index 04cf568c..3956f5ea 100644 --- a/crates/punktfunk-host/src/main.rs +++ b/crates/punktfunk-host/src/main.rs @@ -283,6 +283,24 @@ fn real_main() -> Result<()> { // PASS/FAIL + max Y/Cb/Cr error. #[cfg(target_os = "windows")] Some("hdr-p010-selftest") => crate::capture::dxgi::hdr_p010_selftest(), + // Linux HDR readiness probe (GNOME 50+ portal path): prints whether a monitor is currently + // in BT.2100 (HDR) colour mode, whether the NVENC/VAAPI backend probes Main10 for + // HEVC/AV1, and the GameStream HDR capability the two combine into — the "why isn't my + // stream HDR?" diagnostic (no display/session needed for the encoder half). + #[cfg(target_os = "linux")] + Some("hdr-probe") => { + let monitor_hdr = pf_capture::gnome_hdr_monitor_active(); + let hevc10 = encode::can_encode_10bit(encode::Codec::H265); + let av110 = encode::can_encode_10bit(encode::Codec::Av1); + println!("monitor in BT.2100 (HDR) colour mode: {monitor_hdr}"); + println!("encoder Main10 (HEVC): {hevc10}"); + println!("encoder 10-bit (AV1): {av110}"); + println!( + "GameStream HDR capable (PUNKTFUNK_10BIT + video_source=portal + encoder): {}", + gamestream::host_hdr_capable() + ); + Ok(()) + } // Compositor readiness probe: exit 0 iff the (detected or PUNKTFUNK_COMPOSITOR-forced) // compositor is up and able to create a virtual output *now*. A session-bringup // script polls this to gate on real readiness instead of a blind `sleep`. diff --git a/crates/punktfunk-host/src/native/handshake.rs b/crates/punktfunk-host/src/native/handshake.rs index 47e2543e..8f5779aa 100644 --- a/crates/punktfunk-host/src/native/handshake.rs +++ b/crates/punktfunk-host/src/native/handshake.rs @@ -212,10 +212,22 @@ pub(super) async fn negotiate( // label that matches the stream. let host_wants_10bit = pf_host_config::config().ten_bit; let client_supports_10bit = hello.video_caps & punktfunk_core::quic::VIDEO_CAP_10BIT != 0; + // The capture side must be able to deliver a 10-bit HDR source for the NATIVE plane's + // virtual-output capture — the honest-downgrade gate, mirroring `capturer_supports_444`. + // Windows IDD-push can (it proactively enables advanced colour); Linux cannot: Mutter's + // RecordVirtual virtual-monitor streams are 8-bit-only upstream (GNOME 50 added HDR for + // *monitor* streams only — the GameStream portal-mirror path uses that; see + // `gamestream::host_hdr_capable`), so a Linux native session honestly stays 8-bit SDR even + // though `can_encode_10bit` now probes true on a Main10-capable GPU. + let capture_supports_hdr = crate::capture::capturer_supports_hdr(); // The GPU probe may open a tiny encoder on first use, so run it off the reactor like the // 4:4:4 probe below (blocking probes → spawn_blocking), short-circuited behind the cheap // gates. The result is cached process-wide per (GPU, codec). - let gpu_can_10bit = if host_wants_10bit && client_supports_10bit && codec.supports_10bit() { + let gpu_can_10bit = if host_wants_10bit + && client_supports_10bit + && codec.supports_10bit() + && capture_supports_hdr + { tokio::task::spawn_blocking(move || crate::encode::can_encode_10bit(codec)) .await .context("10-bit capability probe task")? @@ -227,6 +239,7 @@ pub(super) async fn negotiate( bit_depth, host_wants_10bit, client_supports_10bit, + capture_supports_hdr, codec = ?codec, gpu_can_10bit, client_video_caps = hello.video_caps, diff --git a/crates/punktfunk-host/src/session_plan.rs b/crates/punktfunk-host/src/session_plan.rs index 4bcd95e1..f34dafda 100644 --- a/crates/punktfunk-host/src/session_plan.rs +++ b/crates/punktfunk-host/src/session_plan.rs @@ -89,7 +89,9 @@ pub struct SessionPlan { /// Handshake-negotiated encode bit depth (8, or 10 = HEVC Main10). pub bit_depth: u8, /// The IDD-push HDR hint (`bit_depth >= 10`) — the want-HDR flag handed to the capturer so it - /// proactively enables advanced color on the virtual display. Linux is 8-bit (HDR blocked upstream). + /// proactively enables advanced color on the virtual display. The Linux NATIVE plane is 8-bit + /// (Mutter's virtual-monitor streams are SDR-only upstream — GNOME 50 HDR is monitor-mirror + /// only, which the GameStream portal path uses; see `capture::capturer_supports_hdr`). pub hdr: bool, /// Handshake-negotiated chroma subsampling (4:2:0, or full-chroma 4:4:4 when the client + host + /// GPU all support it). Resolved before the Welcome; `Yuv420` on every backend that declined it. diff --git a/crates/punktfunk-host/src/spike.rs b/crates/punktfunk-host/src/spike.rs index 0e22f8e5..4adc047d 100644 --- a/crates/punktfunk-host/src/spike.rs +++ b/crates/punktfunk-host/src/spike.rs @@ -87,8 +87,11 @@ pub fn run(opts: Options) -> Result<()> { } } Source::Portal => { - tracing::info!("spike source: xdg ScreenCast portal (live monitor)"); - capture::open_portal_monitor().context("open portal capturer")? + // PUNKTFUNK_SPIKE_HDR=1: run the GNOME 50+ HDR offer (10-bit PQ dmabufs) — the dev + // validation lever for the Linux HDR capture path without a full GameStream client. + let want_hdr = std::env::var("PUNKTFUNK_SPIKE_HDR").as_deref() == Ok("1"); + tracing::info!(want_hdr, "spike source: xdg ScreenCast portal (live monitor)"); + capture::open_portal_monitor(want_hdr).context("open portal capturer")? } Source::KwinVirtual => { let compositor = crate::vdisplay::detect().unwrap_or(crate::vdisplay::Compositor::Kwin); diff --git a/docs-site/content/docs/configuration.md b/docs-site/content/docs/configuration.md index bc1d3e85..adcd5a43 100644 --- a/docs-site/content/docs/configuration.md +++ b/docs-site/content/docs/configuration.md @@ -88,7 +88,7 @@ See your desktop page ([KDE](/docs/kde), [GNOME](/docs/gnome)) for when to set t | Setting | Values | Meaning | |---|---|---| | `PUNKTFUNK_FEC_PCT` | `N` (percent) | Forward-error-correction redundancy for lossy links (the default is sensible for a normal LAN). Higher = more loss-resilient, more bandwidth. | -| `PUNKTFUNK_10BIT` | `1` · `0` *(default on)* | HEVC Main10 / HDR. **On by default** — the host permits 10-bit; a session goes 10-bit only when the client advertises it (behind the client's HDR setting). Set `0` to force 8-bit. **Windows host only** (the Linux host stays 8-bit). | +| `PUNKTFUNK_10BIT` | `1` · `0` *(default on)* | HEVC Main10 / HDR. **On by default** — the host permits 10-bit; a session goes 10-bit only when the client advertises it (behind the client's HDR setting). Set `0` to force 8-bit. Windows host, plus the Linux **GNOME 50+ GameStream desktop mirror** (`PUNKTFUNK_VIDEO_SOURCE=portal`, mirrored monitor in HDR mode — check with `punktfunk-host hdr-probe`). Linux **virtual displays** (native protocol, GameStream default) stay 8-bit: Mutter's virtual-monitor screencast is SDR-only upstream. | | `PUNKTFUNK_444` | `1` · `0` *(default on)* | Full-chroma HEVC 4:4:4 (Range Extensions) — sharper text/desktop, no chroma loss. **On by default** on the host; the client's own 4:4:4 setting (default off) is the real switch. Set `0` to force 4:2:0. **punktfunk/1 native only** (Moonlight stays 4:2:0), HEVC-only, honored only when the client advertises 4:4:4 **and** the GPU supports it (probed; NVENC is the validated path — VAAPI/AMF/QSV decline). Independent of 10-bit. | | `PUNKTFUNK_PYROWAVE_MAX_MBPS` | `N` (Mbps) | Cap the [PyroWave](/docs/pyrowave) Automatic bitrate pin, for a host on a link that the open-loop pin can outrun (e.g. 4:4:4 + HDR at 5120×1440@240 pins ~5.3 Gbps, over a 5GbE link). Unset = no cap. Only affects Automatic (bitrate `0`) PyroWave sessions; an explicit client bitrate bypasses it. | | `PUNKTFUNK_DSCP` | `1` | Opt-in DSCP / `SO_PRIORITY` QoS tagging on the media sockets. No-op on the wire on Windows without a qWAVE policy. | diff --git a/docs-site/content/docs/roadmap.md b/docs-site/content/docs/roadmap.md index 8e368c33..50bd68a9 100644 --- a/docs-site/content/docs/roadmap.md +++ b/docs-site/content/docs/roadmap.md @@ -24,7 +24,7 @@ see [Status & Progress](/docs/status). | Web console + pairing | ✅ | | Concurrent sessions (shared desktop) | ✅ | | Network speed test + bitrate | ✅ | -| HDR / 10-bit streaming | ✅ Windows host · ⛔ Linux host | +| HDR / 10-bit streaming | ✅ Windows host · 🚧 Linux host (GNOME 50+ desktop mirror; virtual displays blocked upstream) | | Surround audio (5.1 / 7.1) | ✅ | | Sub-frame pipelining (latency) | 🔭 | @@ -100,10 +100,14 @@ see [Status & Progress](/docs/status). ## ⛔ Parked / blocked -- **HDR / 10-bit on the *Linux* host.** HDR streaming already works from a - [Windows host](/docs/windows-host) to an HDR-capable client (Windows, Android). On Linux it's - blocked upstream — no shipping compositor emits a 10-bit/HDR capture stream yet — and ready the - moment one does. +- **HDR / 10-bit on the *Linux* host — virtual displays.** GNOME 50 added HDR screencasting for + **monitor** streams, and the host now uses it: the GameStream desktop mirror + (`PUNKTFUNK_VIDEO_SOURCE=portal`) negotiates the 10-bit PQ formats and encodes HEVC Main10 + BT.2020 PQ (`punktfunk-host hdr-probe` reports readiness; on-glass validation pending). What + stays blocked upstream is HDR on **virtual monitors** — Mutter's `RecordVirtual` streams are + still SDR-only (through the GNOME 51 dev branch), so the native protocol and GameStream's + default virtual-display source stream 8-bit until that lands; the host is ready the moment it + does. - **Advanced DualSense voice-coil haptics.** Scoped and shelved (it rides the controller's USB audio interface, with near-zero game support on Linux). Adaptive triggers, rumble, and the lightbar already ship. diff --git a/docs-site/content/docs/status.md b/docs-site/content/docs/status.md index 1c7b2534..3156e56e 100644 --- a/docs-site/content/docs/status.md +++ b/docs-site/content/docs/status.md @@ -35,9 +35,13 @@ host is newer than the Linux host.) - **Zero-copy GPU pipeline.** Captured frames stay on the GPU — dmabuf → CUDA → NVENC on NVIDIA, and VAAPI or Vulkan Video on AMD/Intel — with automatic split-encode at very high resolutions. Stable 240 fps at 5120×1440 has been measured. A GPU-less software H.264 encoder exists as an explicit fallback. -- **HDR (10-bit), on the Windows host.** An HDR Windows desktop is captured and encoded as HEVC - Main10 (BT.2020 PQ) to HDR-capable clients (Windows, Android). Linux hosts stream 8-bit for now — - HDR there is blocked upstream at the compositor. +- **HDR (10-bit).** An HDR Windows desktop is captured and encoded as HEVC Main10 (BT.2020 PQ) to + HDR-capable clients (Windows, Android). On Linux, a **GNOME 50+** host can mirror an HDR monitor + over the GameStream desktop-capture source (`PUNKTFUNK_VIDEO_SOURCE=portal`): the portal + negotiates the 10-bit PQ screencast formats GNOME 50 added and encodes Main10 PQ (run + `punktfunk-host hdr-probe` to check readiness; pending on-glass validation). Linux **virtual + displays** — the native protocol and GameStream's default source — still stream 8-bit: Mutter's + virtual-monitor screencast is SDR-only upstream. - **Secure by default.** A **SPAKE2 PIN pairing** ceremony establishes trust (the host shows a 4-digit PIN; an attacker gets a single online guess, no offline dictionary attack). Trust-on-first-use (TOFU) remains an explicit opt-in for fully trusted LANs.