unom/punktfunk
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 4 Wiki Activity

feat(windows-host): activate render-adapter pin; gamepad SHM from proto (audit §4.2h/§6.1)

Browse Source 
§4.2h (C2): the host already pins the discrete GPU via IOCTL_SET_RENDER_ADAPTER on the IDD-push path; now that the pf-vdisplay driver implements it (0a7ae5e), correct the stale 'driver returns STATUS_NOT_IMPLEMENTED / STEP-4 stub' comments. Hybrid iGPU+dGPU boxes now actually pin the NVENC GPU.

§6.1 (C5): switch the host gamepad SHM consumers (inject/{dualsense,gamepad}_windows.rs) to derive size/offsets/magic/name from pf_vdisplay_proto::gamepad::{PadShm,XusbShm} via offset_of!/size_of!/helpers, instead of hand-literal OFF_*/140 — proto is now the single source of truth (driver-side switch follows with the gamepad-driver unification). The DualShock4 backend reuses the same pub(super) consts unchanged.

Verified: host clippy (nvenc) clean on the RTX box (x86_64-pc-windows-msvc).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Enrico Bühler
2026-06-25 13:02:22 +00:00
parent 0a7ae5ef09
commit e5c9ee8327
3 changed files with 40 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/punktfunk-host/src/inject/dualsense_windows.rs
+14 -10
View File
@@ -40,17 +40,21 @@ use windows::Win32::System::Memory::{
};
use windows::Win32::System::Threading::{CreateEventW, SetEvent, WaitForSingleObject};
/// Shared-section layout — must match `packaging/windows/dualsense-driver/src/lib.rs`. `pub(super)`
/// so the sibling DualShock 4 backend ([`super::dualshock4_windows`]) reuses the exact offsets.
pub(super) const SHM_SIZE: usize = 256;
pub(super) const SHM_MAGIC: u32 = 0x5046_4453; // "PFDS"
pub(super) const OFF_INPUT: usize = 8;
pub(super) const OFF_OUT_SEQ: usize = 72;
pub(super) const OFF_OUTPUT: usize = 76;
/// Shared-section layout — the single source of truth is [`pf_vdisplay_proto::gamepad::PadShm`] (offset
/// asserts pin every field; the `pf_dualsense` driver maps the same struct). Derive the size/offsets/magic
/// from it so a layout change is a compile error, not a hand-synced literal (audit §6.1). `pub(super)` so
/// the sibling DualShock 4 backend ([`super::dualshock4_windows`]) reuses the exact offsets.
pub(super) const SHM_SIZE: usize = core::mem::size_of::<pf_vdisplay_proto::gamepad::PadShm>();
pub(super) const SHM_MAGIC: u32 = pf_vdisplay_proto::gamepad::PAD_MAGIC; // "PFDS"
pub(super) const OFF_INPUT: usize = core::mem::offset_of!(pf_vdisplay_proto::gamepad::PadShm, input);
pub(super) const OFF_OUT_SEQ: usize =
core::mem::offset_of!(pf_vdisplay_proto::gamepad::PadShm, out_seq);
pub(super) const OFF_OUTPUT: usize = core::mem::offset_of!(pf_vdisplay_proto::gamepad::PadShm, output);
/// Device-type selector the driver reads to choose which HID identity/descriptor it serves: 0 =
/// DualSense (the default — the section is zeroed), 1 = DualShock 4.
pub(super) const OFF_DEVTYPE: usize = 140;
pub(super) const DEVTYPE_DUALSHOCK4: u8 = 1;
pub(super) const OFF_DEVTYPE: usize =
core::mem::offset_of!(pf_vdisplay_proto::gamepad::PadShm, device_type);
pub(super) const DEVTYPE_DUALSHOCK4: u8 = pf_vdisplay_proto::gamepad::DEVTYPE_DUALSHOCK4;
/// A single virtual DualSense: the SwDeviceCreate'd `pf_pad_<index>` software devnode (the driver
/// loads on it and the HID DualSense appears to games) plus the shared-memory section the driver maps.
@@ -239,7 +243,7 @@ pub(super) fn create_swdevice(p: &SwDeviceProfile) -> Result<HSWDEVICE> {
/// caller stamps the device-type + initial input report and finally the magic. Shared by both Windows
/// pad backends (DualSense + DualShock 4).
pub(super) fn create_shm_section(index: u8) -> Result<(HANDLE, *mut u8)> {
let name = HSTRING::from(format!("Global\\pfds-shm-{index}"));
let name = HSTRING::from(pf_vdisplay_proto::gamepad::pad_shm_name(index));
let mut psd = PSECURITY_DESCRIPTOR::default();
// SAFETY: the SDDL literal is valid; psd receives an allocated descriptor (freed by the OS when
crates/punktfunk-host/src/inject/gamepad_windows.rs
+17 -14
View File
@@ -32,19 +32,22 @@ use windows::Win32::System::Memory::{
};
use windows::Win32::System::Threading::{CreateEventW, SetEvent, WaitForSingleObject};
// Shared-section layout — must match `packaging/windows/xusb-driver/src/lib.rs`.
const SHM_SIZE: usize = 64;
const SHM_MAGIC: u32 = 0x5558_4650; // "PFXU"
const OFF_PACKET: usize = 4;
const OFF_BUTTONS: usize = 8;
const OFF_LT: usize = 10;
const OFF_RT: usize = 11;
const OFF_LX: usize = 12;
const OFF_LY: usize = 14;
const OFF_RX: usize = 16;
const OFF_RY: usize = 18;
const OFF_RUMBLE_SEQ: usize = 24;
const OFF_RUMBLE: usize = 28; // large @28, small @29
// Shared-section layout — the single source of truth is `pf_vdisplay_proto::gamepad::XusbShm` (offset
// asserts pin every field; the `pf_xusb` driver maps the same struct). Derive the size/offsets/magic from
// it so a layout change is a compile error, not a hand-synced literal (audit §6.1).
use pf_vdisplay_proto::gamepad::XusbShm;
const SHM_SIZE: usize = core::mem::size_of::<XusbShm>();
const SHM_MAGIC: u32 = pf_vdisplay_proto::gamepad::XUSB_MAGIC; // "PFXU"
const OFF_PACKET: usize = core::mem::offset_of!(XusbShm, packet);
const OFF_BUTTONS: usize = core::mem::offset_of!(XusbShm, buttons);
const OFF_LT: usize = core::mem::offset_of!(XusbShm, left_trigger);
const OFF_RT: usize = core::mem::offset_of!(XusbShm, right_trigger);
const OFF_LX: usize = core::mem::offset_of!(XusbShm, thumb_lx);
const OFF_LY: usize = core::mem::offset_of!(XusbShm, thumb_ly);
const OFF_RX: usize = core::mem::offset_of!(XusbShm, thumb_rx);
const OFF_RY: usize = core::mem::offset_of!(XusbShm, thumb_ry);
const OFF_RUMBLE_SEQ: usize = core::mem::offset_of!(XusbShm, rumble_seq);
const OFF_RUMBLE: usize = core::mem::offset_of!(XusbShm, rumble_large); // large @28, small @29
/// Context for the `SwDeviceCreate` completion callback: an event to signal + the HRESULT it reports.
#[repr(C)]
@@ -157,7 +160,7 @@ struct XusbWinPad {
impl XusbWinPad {
/// Create + map `Global\pfxusb-shm-<index>`, stamp the magic, then spawn the devnode.
fn open(index: u8) -> Result<XusbWinPad> {
let name = HSTRING::from(format!("Global\\pfxusb-shm-{index}"));
let name = HSTRING::from(pf_vdisplay_proto::gamepad::xusb_shm_name(index));
// Permissive DACL so the WUDFHost (whatever account) can open the section.
let mut psd = PSECURITY_DESCRIPTOR::default();
crates/punktfunk-host/src/vdisplay/pf_vdisplay.rs
+9 -9
View File
@@ -245,16 +245,17 @@ unsafe fn create_monitor(device: isize, mode: Mode, watchdog_s: u32) -> Result<M
// SET_RENDER_ADAPTER is OPT-IN. By default we do NOT pin the render adapter — let the IDD use
// its natural adapter (Apollo-parity; avoids the cross-GPU mismatch ACCESS_LOST storm). Opt in
// with PUNKTFUNK_RENDER_ADAPTER=<name substring> or the IDD-push path (which MUST run NVENC on
// the discrete render GPU it pins here). NOTE: the pf-vdisplay driver currently returns
// STATUS_NOT_IMPLEMENTED for this IOCTL (a STEP-4 stub), so the call below is tolerated to fail.
// the discrete render GPU it pins here). The pf-vdisplay driver now IMPLEMENTS this IOCTL
// (IddCxAdapterSetRenderAdapter); a failure is still tolerated (the driver also reports its real
// render LUID in the shared header, so the host binds to the right GPU regardless).
let pinned = if std::env::var("PUNKTFUNK_RENDER_ADAPTER").is_ok() {
unsafe { resolve_render_adapter_luid() }
} else if std::env::var_os("PUNKTFUNK_IDD_PUSH").is_some() {
// P2 direct frame push: the host opens the driver's shared textures AND runs NVENC on the
// RENDER adapter, so on a hybrid box (dGPU + iGPU) it MUST be the discrete encoder GPU — an
// iGPU-rendered surface is untouchable by NVENC. pf-vdisplay HONORS SET_RENDER_ADAPTER (once
// implemented), so pin the discrete GPU; the driver also reports the resulting render LUID in
// the shared header, so the host binds correctly even if this is overridden.
// iGPU-rendered surface is untouchable by NVENC. pf-vdisplay now IMPLEMENTS
// SET_RENDER_ADAPTER, so pin the discrete GPU; the driver also reports the resulting render LUID
// in the shared header, so the host binds correctly even if this is overridden.
tracing::info!("IDD push: pinning the discrete render GPU (SET_RENDER_ADAPTER)");
unsafe { resolve_render_adapter_luid() }
} else {
@@ -270,11 +271,10 @@ unsafe fn create_monitor(device: isize, mode: Mode, watchdog_s: u32) -> Result<M
luid = format!("{:08x}:{:08x}", luid.HighPart, luid.LowPart),
"pf-vdisplay SET_RENDER_ADAPTER: pinned IDD render GPU"
),
// The driver currently stubs this IOCTL (STATUS_NOT_IMPLEMENTED) — warn + continue, do
// NOT propagate. The natural-adapter path still works (Apollo-parity).
// Non-fatal: warn + continue (do NOT propagate). The driver reports its real render LUID
// in the shared header and the host binds to that, so the natural-adapter path still works.
Err(e) => tracing::warn!(
"pf-vdisplay SET_RENDER_ADAPTER failed (driver stub / not implemented — \
continuing): {e:#}"
"pf-vdisplay SET_RENDER_ADAPTER failed (continuing on the natural adapter): {e:#}"
),
}
}