enricobuehler
16a00563a8
Scaffolding for dmabuf zero-copy (plan §9), opt-in via LUMEN_ZEROCOPY:
- src/zerocopy/{cuda,egl}.rs: hand-rolled CUDA Driver-API FFI (no Rust crate
exposes the EGL-interop calls / CUeglFrame) with a shared process-wide
CUcontext + pitched device buffers; an EGL importer (GBM platform on the
NVIDIA render node) that turns a dmabuf into an EGLImage, registers it with
CUDA, and copies it device-to-device into an owned buffer. `zerocopy-probe`
subcommand validates the FFI/linking/GPU access — confirmed on the box
(driver 595, EGL_EXT_image_dma_buf_import + modifiers).
- CapturedFrame gains a FramePayload enum (Cpu(Vec<u8>) | Cuda(DeviceBuffer));
the encoder branches: CPU keeps the expand+upload path, CUDA wraps the device
buffer in an AV_PIX_FMT_CUDA frame fed straight to hevc_nvenc (sharing our
CUcontext via a hand-declared AVCUDADeviceContext, since ffmpeg-sys doesn't
bind hwcontext_cuda.h). open_video/the encoder take a `cuda` flag derived from
the first frame's payload.
The capture-side dmabuf negotiation (which produces the Cuda frames) is the
next step; the CPU path is unchanged and remains the default + fallback. Builds
clean, clippy clean, tests pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
66 lines
3.0 KiB
TOML
66 lines
3.0 KiB
TOML
[package]
|
|
name = "lumen-host"
|
|
description = "lumen Linux streaming host: virtual display, capture, encode, input injection"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
license.workspace = true
|
|
authors.workspace = true
|
|
repository.workspace = true
|
|
|
|
[dependencies]
|
|
lumen-core = { path = "../lumen-core" }
|
|
anyhow = "1"
|
|
tracing = "0.1"
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
|
axum = "0.8"
|
|
mdns-sd = "0.20"
|
|
tokio = { version = "1", features = ["full"] }
|
|
rsa = "0.9"
|
|
sha2 = { version = "0.10", features = ["oid"] }
|
|
aes = "0.8"
|
|
aes-gcm = "0.10"
|
|
cbc = { version = "0.1", features = ["alloc"] }
|
|
rand = "0.8"
|
|
hex = "0.4"
|
|
rcgen = { version = "0.13", default-features = false, features = ["aws_lc_rs", "pem"] }
|
|
x509-parser = "0.16"
|
|
axum-server = { version = "0.7", features = ["tls-rustls"] }
|
|
rustls = "0.23"
|
|
rustls-pemfile = "2"
|
|
rusty_enet = "0.4"
|
|
|
|
[target.'cfg(target_os = "linux")'.dependencies]
|
|
# `screencast` gates the ScreenCast portal module; `remote_desktop` adds the RemoteDesktop
|
|
# portal we use for libei input on KWin/GNOME; `tokio` is the default runtime.
|
|
# `open_pipe_wire_remote` is unconditional, so ashpd's own `pipewire` feature is not
|
|
# needed — we drive PipeWire with the `pipewire` crate below.
|
|
ashpd = { version = "0.13", features = ["screencast", "remote_desktop"] }
|
|
ffmpeg-next = "7"
|
|
libc = "0.2"
|
|
# Must match the pipewire crate ashpd 0.13 links (libspa/pipewire-sys `links` key is
|
|
# unique per build), i.e. 0.9 — NOT the 0.10 the setup doc mentions.
|
|
pipewire = "0.9"
|
|
# ashpd 0.13 uses the tokio runtime; a current-thread runtime drives the one-time
|
|
# portal handshake (control plane — never the per-frame path).
|
|
tokio = { version = "1", features = ["rt", "rt-multi-thread", "net", "time"] }
|
|
# Input injection into headless Sway via the wlroots virtual-input Wayland protocols
|
|
# (uinput won't reach a compositor running with WLR_LIBINPUT_NO_DEVICES=1).
|
|
wayland-client = "0.31"
|
|
wayland-protocols-wlr = { version = "0.3", features = ["client"] }
|
|
wayland-protocols-misc = { version = "0.3", features = ["client"] }
|
|
# Builds/validates the xkb keymap uploaded to the virtual keyboard + tracks modifier state.
|
|
xkbcommon = "0.8"
|
|
# Opus encode for the GameStream audio stream (links system libopus).
|
|
opus = "0.3"
|
|
# libei (EI sender) for the portable input path on KWin/GNOME (RemoteDesktop portal).
|
|
# The `tokio` feature wires reis's event stream into tokio's reactor.
|
|
reis = { version = "0.6.1", features = ["tokio"] }
|
|
# `StreamExt::next` on reis's tokio event stream in the libei worker loop.
|
|
futures-util = "0.3"
|
|
# Zero-copy capture (plan §9): EGL imports the PipeWire dmabuf, CUDA maps it, NVENC encodes
|
|
# it with no CPU roundtrip. `khronos-egl` (dynamic = load the NVIDIA libEGL at runtime) gives
|
|
# eglCreateImage + the dma_buf import; the CUDA driver API (EGL interop) and libgbm are linked
|
|
# via hand-rolled FFI in `src/zerocopy/` (no Rust crate exposes the EGL-interop driver calls).
|
|
khronos-egl = { version = "6", features = ["dynamic"] }
|