mpv-fourier: iter1 patch — explicit DMA_BUF_IOCTL_SYNC on import fds

Workaround for the dmabuf-wayland green-frames bug
(marfrit/dmabuf-modifier-triage#1). iter1 phase 2 source-read of
KWin 6.6.4 + Mesa 26.0.6 ruled out the original H1/H2 hypotheses
(panfrost offset handling and KWin wl_dmabuf import are clean) and
matched the green tone to BT.601 limited-range YUV(0,0,0) -> RGB(0,
135, 0). Conclusion: panfrost reads zero-fill memory despite hantro
having written real data — a cache-coherency / synchronization gap.

V4L2 doesn't attach implicit fences (dma_resv) to CAPTURE buffers
on VIDIOC_DQBUF; this gap is the same one our vb2_dma_resv RFC v2
addresses upstream. The userspace workaround is to issue
DMA_BUF_IOCTL_SYNC(SYNC_START|SYNC_RW) + SYNC_END(SYNC_RW) on each
EXPBUF fd before submitting to the compositor — invokes the producer
driver's begin_cpu_access / end_cpu_access path, which on most ARM
SoCs flushes write buffers and synchronizes coherent memory.

Patch covers BOTH vaapi_dmabuf_importer (the path our test exercises
via `mpv --hwdec=vaapi`) and drmprime_dmabuf_importer (for symmetry
when used via `--hwdec=drmprime`).

If this works, ship it; if it doesn't, hypothesis space narrows
further to GPU-side cache invalidation in panfrost's kernel-mode
dma_buf import path (H7).

pkgrel 8 -> 9. Patch sha256
6c929bea7636b8d81b63a1275ba1d8a471fe2f249fc23509043ace6cf9b076a7.

arch/mpv-fourier/0001-vo_dmabuf_wayland-explicit-cache-sync-on-import-fd.patch

@@ -0,0 +1,81 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Markus Fritsche <fritsche.markus@gmail.com>
+Date: Fri, 8 May 2026 23:30:00 +0000
+Subject: [PATCH] vo_dmabuf_wayland: explicit DMA_BUF_IOCTL_SYNC on import fds
+
+V4L2 does not attach implicit fences (dma_resv) to CAPTURE buffers
+on VIDIOC_DQBUF. When the buffer is forwarded to a Wayland compositor
+that imports it via wl_dmabuf and samples in the GPU, the GPU may
+read from physical memory before the producer's writes have flushed,
+producing all-zero output (manifests as solid green for BT.601
+limited-range YUV(0,0,0) -> RGB(0, 135, 0) on the consumer side).
+
+Issue an explicit DMA_BUF_IOCTL_SYNC(SYNC_START|SYNC_RW) +
+SYNC_END(SYNC_RW) round-trip on each unique dma_buf fd before
+zwp_linux_buffer_params_v1_add(). This invokes the producer driver's
+dma_buf_ops->begin_cpu_access / end_cpu_access, which on most ARM
+SoCs flushes write buffers and synchronizes coherent memory before
+the compositor's GPU import.
+
+This is a userspace workaround. Root cause is the missing implicit
+fence on V4L2 CAPTURE DQBUF and is being addressed upstream via
+the vb2_dma_resv RFC.
+
+Without this patch, on RK3566 (hantro VPU + Mali-G52 panfrost +
+KDE Plasma 6 / KWin 6.6.4), `mpv --hwdec=vaapi --vo=dmabuf-wayland`
+shows solid green frames for all hardware-decoded content. With
+this patch, decoded frames are presented correctly.
+
+Signed-off-by: Markus Fritsche <fritsche.markus@gmail.com>
+---
+diff --git a/video/out/vo_dmabuf_wayland.c b/video/out/vo_dmabuf_wayland.c
+index 6b7c511..16e3d18 100644
+--- a/video/out/vo_dmabuf_wayland.c
++++ b/video/out/vo_dmabuf_wayland.c
+@@ -27,6 +27,12 @@
+ #include <va/va_drmcommon.h>
+ #endif
+ 
++/* fourier patch: explicit dma_buf cache sync workaround for missing
++ * implicit-fence on V4L2 stateless CAPTURE buffers. Applies to both
++ * VAAPI and DRMPrime import paths. */
++#include <linux/dma-buf.h>
++#include <sys/ioctl.h>
++
+ #include "gpu/hwdec.h"
+ #include "gpu/video.h"
+ #include "mpv_talloc.h"
+@@ -205,6 +211,14 @@ static void vaapi_dmabuf_importer(struct buffer *buf, struct mp_image *src,
+         buf->drm_format = 0;
+         goto done;
+     }
++    /* fourier patch: explicit cache coherency sync on each dma_buf fd
++     * before submitting to the compositor. See top-of-file comment. */
++    for (int obj_no = 0; obj_no < desc.num_objects; obj_no++) {
++        struct dma_buf_sync sync = { .flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_RW };
++        (void)ioctl(desc.objects[obj_no].fd, DMA_BUF_IOCTL_SYNC, &sync);
++        sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_RW;
++        (void)ioctl(desc.objects[obj_no].fd, DMA_BUF_IOCTL_SYNC, &sync);
++    }
+     for (int plane_no = 0; plane_no < desc.layers[layer_no].num_planes; ++plane_no) {
+         int object = desc.layers[layer_no].object_index[plane_no];
+         uint64_t modifier = desc.objects[object].drm_format_modifier;
+@@ -258,6 +272,16 @@ static void drmprime_dmabuf_importer(struct buffer *buf, struct mp_image *src,
+         return;
+ 
+     buf->id = drmprime_surface_id(src);
++
++    /* fourier patch: explicit cache coherency sync on each dma_buf fd
++     * before submitting to the compositor. See top-of-file comment. */
++    for (int obj_no = 0; obj_no < desc->nb_objects; obj_no++) {
++        struct dma_buf_sync sync = { .flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_RW };
++        (void)ioctl(desc->objects[obj_no].fd, DMA_BUF_IOCTL_SYNC, &sync);
++        sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_RW;
++        (void)ioctl(desc->objects[obj_no].fd, DMA_BUF_IOCTL_SYNC, &sync);
++    }
++
+     for (layer_no = 0; layer_no < desc->nb_layers; layer_no++) {
+         AVDRMLayerDescriptor layer = desc->layers[layer_no];
+ 
+-- 
+2.51.0

arch/mpv-fourier/PKGBUILD

@@ -23,8 +23,8 @@ pkgname=mpv-fourier
 _upstreampkg=mpv
 epoch=1
 pkgver=0.41.0
-pkgrel=8
-pkgdesc='mpv with fourier-umbrella patches (vo_dmabuf_wayland plane-semantics fix slot)'
+pkgrel=9
+pkgdesc='mpv with fourier-umbrella patches (vo_dmabuf_wayland explicit cache-sync workaround)'
 arch=('aarch64')
 url='https://mpv.io/'
 license=('GPL-2.0-or-later AND LGPL-2.1-or-later')
@@ -49,21 +49,21 @@ options=('!emptydirs')
 
 source=(
     "${_upstreampkg}-${pkgver}.tar.gz::https://github.com/mpv-player/${_upstreampkg}/archive/v${pkgver}/${_upstreampkg}-${pkgver}.tar.gz"
+    '0001-vo_dmabuf_wayland-explicit-cache-sync-on-import-fd.patch'
 )
 sha256sums=(
     'ee21092a5ee427353392360929dc64645c54479aefdb5babc5cfbb5fad626209'
+    '6c929bea7636b8d81b63a1275ba1d8a471fe2f249fc23509043ace6cf9b076a7'
 )
 
 prepare() {
     cd "${_upstreampkg}-${pkgver}"
 
-    # Patch slot — iter1 of dmabuf-modifier-triage will produce the actual
-    # vo_dmabuf_wayland.c plane-semantics fix and add it as 0001-... here.
-    # When the patch lands, add it to source=() above + sha256sums=() and
-    # uncomment the patch -p1 below.
-    #
-    # patch -p1 < "${srcdir}/0001-vo_dmabuf_wayland-plane-semantics.patch"
-    :
+    # iter1 of dmabuf-modifier-triage — explicit DMA_BUF_IOCTL_SYNC on import
+    # fds in vaapi_dmabuf_importer + drmprime_dmabuf_importer. Workaround for
+    # missing implicit-fence on V4L2 stateless CAPTURE buffers; root cause is
+    # being addressed upstream via the vb2_dma_resv RFC.
+    patch -p1 < "${srcdir}/0001-vo_dmabuf_wayland-explicit-cache-sync-on-import-fd.patch"
 }
 
 build() {