//! Frame capture (plan §7). On Linux: a PipeWire ScreenCast portal stream. The spike uses the //! CPU-copy fallback (the portal delivers a CPU buffer; the encoder uploads it to the GPU //! internally). Zero-copy dmabuf→NVENC import is deferred (plan §9 risk). // Every unsafe block in this module tree carries a `// SAFETY:` proof; enforce it (unsafe-proof // program). As a parent module this also covers the child modules (capture::windows/linux::*). #![deny(clippy::undocumented_unsafe_blocks)] use anyhow::Result; // The shared frame vocabulary lives in the `pf-frame` leaf crate (plan §W6); re-export it here so // every existing `crate::capture::{PixelFormat, CapturedFrame, …}` path stays valid. pub use pf_frame::{CapturedFrame, FramePayload, OutputFormat, PixelFormat}; // `CursorOverlay` (cursor-as-metadata) and the dmabuf vocabulary are named only by the Linux // capture/encode paths; gate the re-exports so the Windows build doesn't flag them unused. #[cfg(target_os = "linux")] pub use pf_frame::{drm_fourcc, CursorOverlay, DmabufFrame}; /// Produces frames from a captured output. Lives on its own thread, feeding the encoder /// over a bounded drop-oldest channel (never block the compositor). pub trait Capturer: Send { fn next_frame(&mut self) -> Result; /// Non-blocking: the freshest frame available since the last call, or `None` if none has /// arrived (the caller reuses its last frame to hold a steady output rate). The default /// just produces a frame each call — fine for instant synthetic sources; the portal /// overrides it to drain its channel without blocking. fn try_latest(&mut self) -> Result> { self.next_frame().map(Some) } /// Gate expensive per-frame work so the capturer can be kept alive (reused) between /// streams without burning CPU. The portal capturer skips the de-pad copy while inactive; /// the default is a no-op (synthetic sources are produced on demand). Set `true` for the /// duration of a stream, `false` when it ends. fn set_active(&self, _active: bool) {} /// The source's static HDR mastering metadata (SMPTE ST.2086 + content light level), when the /// capturer can read it from the output (Windows `IDXGIOutput6::GetDesc1`). `None` = unknown / /// SDR / a backend that doesn't expose it (the default — Linux capture has no HDR path yet). /// The stream loop forwards this to the encoder (in-band SEI) and the client (`0xCE` datagram), /// so the two stay a single source of truth. May change mid-session if the source is regraded. fn hdr_meta(&self) -> Option { None } /// How many frames the encode loop may keep in flight (submitted but not yet polled) before it /// blocks. `1` (the default) is the synchronous loop: capture → submit → poll-blocks, so the /// per-frame wall time is `capture+convert + encode`. A capturer that hands a fresh output texture /// per frame (so the encode of N reads a different texture than the convert of N+1 writes) can return /// `>1` to PIPELINE: the loop submits N+1 before polling N, overlapping the convert/copy on the 3D /// engine with the NVENC-ASIC encode of the prior frame, dropping per-frame wall toward `max(...)`. fn pipeline_depth(&self) -> usize { 1 } } /// A deterministic moving test pattern (BGRx). Lets the spike exercise the encode → file → /// `punktfunk_core` path with no live capture session, and produces obviously non-static /// content (a sweeping bar + animated gradient) so the encoded output is verifiable. pub struct SyntheticCapturer { width: u32, height: u32, fps: u32, frame_idx: u64, buf: Vec, } impl SyntheticCapturer { const BPP: usize = 4; // emits BGRx pub fn new(width: u32, height: u32, fps: u32) -> Self { assert!(width > 0 && height > 0 && fps > 0); let buf = vec![0u8; width as usize * height as usize * Self::BPP]; SyntheticCapturer { width, height, fps, frame_idx: 0, buf, } } } impl Capturer for SyntheticCapturer { fn next_frame(&mut self) -> Result { let w = self.width as usize; let h = self.height as usize; let bpp = Self::BPP; let t = self.frame_idx; // A vertical bar sweeps left→right once every ~2s; the background is a gradient // whose phase advances each frame, so every pixel changes frame-to-frame. let bar_x = ((t * w as u64) / (self.fps as u64 * 2)) % w as u64; let phase = (t % 256) as usize; for y in 0..h { let row = y * w * bpp; for x in 0..w { let i = row + x * bpp; let on_bar = (x as u64).abs_diff(bar_x) < 8; // BGRx byte order: [B, G, R, x] self.buf[i] = if on_bar { 255 } else { ((x + phase) & 0xff) as u8 }; self.buf[i + 1] = if on_bar { 255 } else { ((y + phase) & 0xff) as u8 }; self.buf[i + 2] = if on_bar { 255 } else { ((x + y) & 0xff) as u8 }; self.buf[i + 3] = 0; } } let pts_ns = self.frame_idx * 1_000_000_000 / self.fps as u64; self.frame_idx += 1; Ok(CapturedFrame { width: self.width, height: self.height, pts_ns, format: PixelFormat::Bgrx, payload: FramePayload::Cpu(self.buf.clone()), cursor: None, }) } } /// A cheap moving test pattern (BGRx) for the streaming path: a pulsing field + a white band /// sweeping down, generated with whole-buffer `fill`s so it stays real-time even at 5K. pub struct FastSyntheticCapturer { width: u32, height: u32, frame_idx: u64, buf: Vec, /// PUNKTFUNK_SYNTH_NOISE: every frame is fresh high-entropy noise NVENC can't compress or /// predict, so the encoder hits its (CBR) bitrate target — a throughput test of the real /// encode→FEC→send→recv path. The default flat/band content compresses to ~nothing, so it /// can't generate real Mbps (the encoder is content-driven). xorshift over u64 chunks. noise: bool, rng: u64, } impl FastSyntheticCapturer { pub fn new(width: u32, height: u32) -> Self { assert!(width > 0 && height > 0); FastSyntheticCapturer { width, height, frame_idx: 0, buf: vec![0u8; width as usize * height as usize * 4], noise: std::env::var_os("PUNKTFUNK_SYNTH_NOISE").is_some(), rng: 0x9e3779b97f4a7c15, } } } impl Capturer for FastSyntheticCapturer { fn next_frame(&mut self) -> Result { if self.noise { // Fresh, every-frame-decorrelated noise: reseed from the frame index so consecutive // frames share no structure (forces large P-frames too, not just the keyframe). let mut s = self .rng .wrapping_add(self.frame_idx.wrapping_mul(0x2545F491_4F6CDD1D)) | 1; for c in self.buf.chunks_exact_mut(8) { s ^= s << 13; s ^= s >> 7; s ^= s << 17; c.copy_from_slice(&s.to_le_bytes()); } self.rng = s; } else { let (w, h) = (self.width as usize, self.height as usize); let row = w * 4; let shade = (self.frame_idx % 256) as u8; self.buf.fill(shade); let band_h = (h / 20).max(1); let band_y = (self.frame_idx as usize * 6) % h; for y in band_y..(band_y + band_h).min(h) { self.buf[y * row..(y + 1) * row].fill(0xff); } } self.frame_idx += 1; Ok(CapturedFrame { width: self.width, height: self.height, pts_ns: 0, format: PixelFormat::Bgrx, payload: FramePayload::Cpu(self.buf.clone()), cursor: None, }) } } /// Open a live capturer for a client-sized monitor via the xdg ScreenCast portal /// (`ashpd`) → PipeWire (`pipewire`). Implemented in the `linux` submodule. #[cfg(target_os = "linux")] pub fn open_portal_monitor() -> 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; linux::PortalCapturer::open(anchored).map(|c| Box::new(c) as Box) } #[cfg(not(target_os = "linux"))] pub fn open_portal_monitor() -> Result> { anyhow::bail!("portal capture requires Linux (xdg-desktop-portal + PipeWire)") } /// Build a capturer from an already-created virtual output (see [`crate::vdisplay`]). Consumes /// the output's PipeWire node + optional remote fd + keepalive — the capturer owns the keepalive, /// so dropping the capturer releases the virtual output. Compositor-agnostic: works for any /// [`crate::vdisplay::VirtualDisplay`] backend. The captured size is the size the output was /// created at — native, no scaling. #[cfg(target_os = "linux")] pub fn capture_virtual_output( vout: crate::vdisplay::VirtualOutput, 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 for tiled dmabufs (the 4:4:4 zero-copy path). `gpu = // false` (4:4:4 without zero-copy) forces the CPU mmap path so the encoder gets CPU-resident // RGB to swscale into YUV444P. linux::PortalCapturer::from_virtual_output(vout, want.gpu, want.chroma_444) .map(|c| Box::new(c) as Box) } #[cfg(target_os = "windows")] pub fn capture_virtual_output( vout: crate::vdisplay::VirtualOutput, want: OutputFormat, _capture: crate::session_plan::CaptureBackend, ) -> Result> { let target = vout.win_capture.clone().ok_or_else(|| { anyhow::anyhow!( "pf-vdisplay target not yet an active display path (activation failed — see the \ virtual-display warnings above)" ) })?; let pref = vout.preferred_mode; let keep = vout.keepalive; // IDD direct-push is the sole Windows capture path: consume frames straight from the pf-vdisplay // driver's shared ring (in-process, Session 0 — it captures the secure desktop too; no Desktop // Duplication, no WGC helper). A FRESH monitor + ring is created per session: a REUSED monitor's // swap-chain dies after ~2 sessions and can't be revived. The ring is always FP16 when the display // is HDR (the driver composes the IDD in FP16); `want.hdr` proactively enables advanced color and // selects the per-frame conversion (FP16 → P010 vs BGRA → NV12, or BGRA → AYUV for a // `want.chroma_444` SDR session). `IddPushCapturer` takes the keepalive (it owns the virtual // display). There is NO fallback (DDA + the WGC relay were removed): if it can't open or the // driver doesn't attach, the session fails cleanly and the client reconnects. idd_push::IddPushCapturer::open(target, pref, want.hdr, want.chroma_444, keep) .map(|c| Box::new(c) as Box) .map_err(|(e, _keep)| e.context("IDD-push capture open (no fallback)")) } /// Whether the active capturer can deliver a full-chroma (RGB) source for a 4:4:4 HEVC encode. The /// negotiator gates 4:4:4 on this so the host honestly downgrades to 4:2:0 when the capturer can only /// produce subsampled frames. `encoder_ingests_rgb_444` is the encoder half of the gate, resolved by /// the caller ([`crate::encode::resolved_backend_ingests_rgb_444`]) and passed **in** so capture never /// re-derives the backend (the one-way capture→encode edge, plan §2.4 / §W4). Linux (the portal capturer /// feeding CPU RGB → `yuv444p`) can regardless; the Windows IDD-push path delivers subsampled NV12/P010 /// today, so full-chroma capture there rides entirely on the encoder gate. #[cfg(target_os = "linux")] pub(crate) fn capturer_supports_444(_encoder_ingests_rgb_444: bool) -> bool { true } #[cfg(target_os = "windows")] pub(crate) 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), // but only a backend that ingests RGB and CSCs it to 4:4:4 itself can use it — today just // direct-NVENC (AMF can't 4:4:4 at all; the QSV/ffmpeg path has no RGB-input 4:4:4 wiring). An HDR // display can't be known here (the virtual display's mode settles after the Welcome); that // combination downgrades at capture time — the capturer emits P010 and the encoder's caps // cross-check reports the 4:2:0 truth (the in-band SPS keeps the client correct either way). encoder_ingests_rgb_444 } #[cfg(not(any(target_os = "linux", target_os = "windows")))] pub(crate) fn capturer_supports_444(_encoder_ingests_rgb_444: bool) -> bool { false } #[cfg(not(any(target_os = "linux", target_os = "windows")))] pub fn capture_virtual_output( _vout: crate::vdisplay::VirtualOutput, _want: OutputFormat, _capture: crate::session_plan::CaptureBackend, ) -> Result> { anyhow::bail!("virtual-output capture requires Linux or Windows") } // Goal-1 stage 6: the Windows backend lives under `capture/windows/`, the Linux one under `capture/linux/` // (`#[path]` keeps the module names flat, so every `crate::capture::*` path is unchanged). Windows capture // is IDD direct-push only — DXGI Desktop Duplication (DDA) and the WGC two-process relay were removed. #[cfg(target_os = "windows")] #[path = "capture/windows/dxgi.rs"] pub mod dxgi; #[cfg(target_os = "windows")] #[path = "capture/windows/idd_push.rs"] pub mod idd_push; #[cfg(target_os = "linux")] mod linux; #[cfg(target_os = "windows")] #[path = "capture/windows/synthetic_nv12.rs"] pub mod synthetic_nv12;