kwin-fourier: bypass watchDmaBuf implicit-sync fence wait (experiment)

Hypothesis under test: KWin's Transaction::watchDmaBuf calls
DMA_BUF_IOCTL_EXPORT_SYNC_FILE on every plane of every imported
dmabuf and parks the transaction on a QSocketNotifier(POLLIN)
waiting for that sync_file. On V4L2 hantro CAPTURE buffers (RK3566
mainline 6.19, panfrost mesa 26.0.5) the resulting fence either
never signals or signals so late that chrome's 6-buffer V4L2
capture pool exhausts at ~6s, hard-stalling the decoder. mpv with
gpu-next slideshows at 76% drop. weston A/B with same chrome v4
binary plays through clean — KWin's watchDmaBuf is the suspect.

This experiment patches watchDmaBuf to no-op. Wayland clients are
required by spec to ensure buffer contents are complete before
wl_surface.attach+commit, so the fence-wait is a defensive
optimization for misbehaving clients, not a correctness primitive.

If chrome plays through end-to-end at the recorded 34.7% combined
CPU number with this patched KWin, the bug is confirmed and the
upstream fix can be refined (timeout, V4L2-source skip, or use the
dmabuf fd directly in the QSocketNotifier instead of an extra
exported sync_file).

KWIN_PIVOT.md (in chromium-fourier/) carries the discovery thread.

arch/kwin-fourier/0001-transaction-bypass-watchDmaBuf-fence-wait.patch

@@ -0,0 +1,89 @@
+From: Markus Fritsche <mfritsche@reauktion.de>
+Subject: [PATCH] transaction: bypass watchDmaBuf implicit-sync fence wait
+Date: 2026-04-28
+
+Background
+----------
+KWin's `Transaction::watchDmaBuf` (src/wayland/transaction.cpp) calls
+`DMA_BUF_IOCTL_EXPORT_SYNC_FILE` on every plane of every imported
+dmabuf and parks the transaction on a `QSocketNotifier(POLLIN)`
+waiting for the resulting sync_file fd to become readable. The intent
+is correct in principle — wait for the producer to finish writing
+before sampling — but on V4L2 hantro CAPTURE buffers (RK3566 mainline
+6.19, panfrost mesa 26.0.5) the resulting fence either signals so
+late that chrome's 6-buffer V4L2 capture pool exhausts, or never
+signals at all. Symptom (per chromium-fourier KWIN_PIVOT.md):
+
+- chrome v4 attaches a video frame to a wp_subsurface, commits
+- KWin's Transaction::commit calls watchDmaBuf, exports a sync_file,
+  parks on QSocketNotifier
+- Sync_file never becomes readable
+- Transaction never applies; old surface state never replaced
+- wl_buffer.release for the previous video buffer never sent
+- chrome's V4L2 capture pool starves at ~6 seconds, decoder blocks,
+  audio drains, hard stall
+
+mpv with `--vo=gpu-next` on the same KWin session slideshows at 76%
+drop rate but does not deadlock — its single-surface attach pattern
+hits a different transaction shape than chrome's subsurface flow.
+
+A clean weston A/B with the same chrome v4 binary plays through
+end-to-end: the bug is specifically KWin's transaction fence-wait
+path on this stack, not Wayland-as-a-protocol.
+
+Fix
+---
+This experimental patch no-ops `watchDmaBuf` to test the hypothesis.
+Implicit-sync correctness in this case is not lost: the V4L2
+producer guarantees the buffer's contents are complete before
+chrome sends `wl_surface.attach + commit`, and the wp_linux_dmabuf
+client is required to do so by spec. The fence-wait was a defensive
+optimization for misbehaving clients, not a correctness primitive.
+
+If chrome plays through end-to-end at the recorded 34.7% combined
+CPU number under KWin with this patch, the bug is confirmed and the
+upstream fix can be refined (timeout, V4L2-source skip, or use the
+dmabuf fd directly in the QSocketNotifier instead of an extra
+exported sync_file).
+
+diff --git a/src/wayland/transaction.cpp b/src/wayland/transaction.cpp
+index 967b22b..e3fbc06 100644
+--- a/src/wayland/transaction.cpp
++++ b/src/wayland/transaction.cpp
+@@ -263,27 +263,18 @@ static FileDescriptor exportWaitSyncFile(const FileDescriptor &fileDescriptor)
+     return FileDescriptor{};
+ }
+ #endif
+ 
+ void Transaction::watchDmaBuf(TransactionEntry *entry)
+ {
+-#if defined(Q_OS_LINUX)
+-    const DmaBufAttributes *attributes = entry->buffer->dmabufAttributes();
+-    if (!attributes) {
+-        return;
+-    }
+-
+-    for (int i = 0; i < attributes->planeCount; ++i) {
+-        const FileDescriptor &fileDescriptor = attributes->fd[i];
+-        if (fileDescriptor.isReadable()) {
+-            continue;
+-        }
+-
+-        auto syncFile = exportWaitSyncFile(fileDescriptor);
+-        if (syncFile.isValid()) {
+-            entry->fences.emplace_back(std::make_unique<TransactionFence>(this, std::move(syncFile)));
+-        }
+-    }
+-#endif
++    // kwin-fourier: no-op the implicit-sync fence wait. On V4L2
++    // hantro CAPTURE buffers (RK3566 mainline 6.19, panfrost mesa
++    // 26.0.5) the DMA_BUF_IOCTL_EXPORT_SYNC_FILE fence either never
++    // signals or signals so late that chrome's V4L2 capture pool
++    // exhausts at ~6s, hard-stalling the decoder. Wayland clients
++    // are required by spec to ensure the buffer's contents are
++    // complete before wl_surface.attach+commit, so this fence-wait
++    // is a belt-and-braces optimization, not a correctness primitive.
++    Q_UNUSED(entry);
+ }
+ 
+ } // namespace KWin

arch/kwin-fourier/PKGBUILD

@@ -0,0 +1,125 @@
+# Maintainer: Markus Fritsche <mfritsche@reauktion.de>
+# Upstream maintainers: Felix Yan, Antonio Rojas
+# Contributor: Andrea Scarpino <andrea@archlinux.org>
+#
+# kwin-fourier — KWin 6.6.4 with the V4L2-stateless implicit-sync
+# transaction wait bypass. Hypothesis: KWin's
+# `Transaction::watchDmaBuf` calls DMA_BUF_IOCTL_EXPORT_SYNC_FILE on
+# every plane of every imported dmabuf and parks the transaction on a
+# QSocketNotifier waiting for the resulting sync_file fd to become
+# readable. For V4L2 hantro CAPTURE buffers on RK3566 mainline 6.19,
+# that fence either never signals or signals so late that chrome's
+# 6-buffer V4L2 capture pool exhausts at ~6 seconds, blocking the
+# decoder. mpv (single-surface attach pattern) merely slideshows
+# under KWin (76% drop rate); chrome (subsurface attach) deadlocks.
+#
+# This experimental build no-ops `watchDmaBuf` to test the
+# hypothesis. If chrome plays through end-to-end at the recorded
+# 34.7% CPU number, the bug is confirmed and the upstream fix can be
+# refined (e.g., short timeout, skip-on-V4L2, or use the dmabuf fd
+# directly without exporting an extra sync_file). See
+# ../chromium-fourier/KWIN_PIVOT.md for the full diagnosis thread.
+
+pkgname=kwin
+pkgver=6.6.4
+_dirver=$(echo $pkgver | cut -d. -f1-3)
+pkgrel=1
+epoch=1
+arch=(aarch64 x86_64)
+url='https://kde.org/plasma-desktop/'
+license=(LGPL-2.0-or-later)
+depends=(aurorae
+         breeze
+         gcc-libs
+         glibc
+         iio-sensor-proxy
+         plasma-activities
+         kauth
+         kcmutils
+         kcolorscheme
+         kconfig
+         kcoreaddons
+         kcrash
+         kdbusaddons
+         kdeclarative
+         kdecoration
+         kglobalaccel
+         kglobalacceld
+         kguiaddons
+         ki18n
+         kidletime
+         kirigami
+         kitemmodels
+         knewstuff
+         knighttime
+         knotifications
+         kpackage
+         kquickcharts
+         kscreenlocker
+         kservice
+         ksvg
+         kwayland
+         kwidgetsaddons
+         kwindowsystem
+         kxmlgui
+         lcms2
+         libcanberra
+         libdisplay-info
+         libdrm
+         libei
+         libepoxy
+         libevdev
+         libinput
+         libpipewire
+         libqaccessibilityclient-qt6
+         libxcb
+         libxcvt
+         libxkbcommon
+         mesa
+         milou
+         pipewire-session-manager
+         libplasma
+         qt6-5compat
+         qt6-base
+         qt6-declarative
+         qt6-svg
+         qt6-tools
+         systemd-libs
+         wayland
+         xcb-util-keysyms
+         xcb-util-wm)
+makedepends=(extra-cmake-modules
+             kdoctools
+             krunner
+             plasma-wayland-protocols
+             python
+             wayland-protocols
+             xorg-xwayland)
+optdepends=('plasma-keyboard: virtual keyboard')
+groups=(plasma)
+source=(https://download.kde.org/stable/plasma/$_dirver/$pkgname-$pkgver.tar.xz{,.sig}
+        0001-transaction-bypass-watchDmaBuf-fence-wait.patch)
+sha256sums=('3f9439760580a977d018daf4b35b62e5a1700def7b21c8dfbfc789d21378d7ad'
+            'SKIP'
+            'SKIP')
+validpgpkeys=('E0A3EB202F8E57528E13E72FD7574483BB57B18D'  # Jonathan Esk-Riddell <jr@jriddell.org>
+              '0AAC775BB6437A8D9AF7A3ACFE0784117FBCE11D'  # Bhushan Shah <bshah@kde.org>
+              'D07BD8662C56CB291B316EB2F5675605C74E02CF'  # David Edmundson <davidedmundson@kde.org>
+              '90A968ACA84537CC27B99EAF2C8DF587A6D4AAC1'  # Nicolas Fella <nicolas.fella@kde.org>
+              '1FA881591C26B276D7A5518EEAAF29B42A678C20') # Marco Martin <notmart@gmail.com>
+
+prepare() {
+  patch -d $pkgname-$pkgver -p1 < 0001-transaction-bypass-watchDmaBuf-fence-wait.patch
+}
+
+build() {
+  cmake -B build  -S $pkgname-$pkgver \
+    -DCMAKE_INSTALL_LIBEXECDIR=lib \
+    -DBUILD_TESTING=OFF
+  cmake --build build
+}
+
+package() {
+  DESTDIR="$pkgdir" cmake --install build
+  setcap CAP_SYS_NICE=+ep "$pkgdir"/usr/bin/kwin_wayland
+}