drm/virtio: Fix type of dma-fence context variable

Type of DMA fence context is u64. Fence-waiting code uses u32 for the
context variable, fix it.

Fixes: e4812ab8e6b1 ("drm/virtio: Refactor and opt

drm/virtio: Fix type of dma-fence context variable

Type of DMA fence context is u64. Fence-waiting code uses u32 for the
context variable, fix it.

Fixes: e4812ab8e6b1 ("drm/virtio: Refactor and optimize job submission code path")
Cc: <[email protected]> # v6.4+
Signed-off-by: Dmitry Osipenko <[email protected]>
Reviewed-by: Rob Clark <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/virtio: Spelling fixes

While making a spelling mistake myself for `git grep kvalloc`
I found that the only file has such a typo. Fix it and update
to the standard de facto of how we refer to the

drm/virtio: Spelling fixes

While making a spelling mistake myself for `git grep kvalloc`
I found that the only file has such a typo. Fix it and update
to the standard de facto of how we refer to the functions.
Also spell usr-out as user-out, it seems this driver uses its
own terminology nobody else can decypher, make it more readable.

Signed-off-by: Andy Shevchenko <[email protected]>
Signed-off-by: Dmitry Osipenko <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/virtio: clean out_fence on complete_submit

The removed line prevents the following cleanup function
to execute a dma_fence_put on the out_fence to free its
memory, producing the following output

drm/virtio: clean out_fence on complete_submit

The removed line prevents the following cleanup function
to execute a dma_fence_put on the out_fence to free its
memory, producing the following output in kmemleak:

unreferenced object 0xffff888126d8ee00 (size 128):
comm "kwin_wayland", pid 981, jiffies 4295380296 (age 390.060s)
hex dump (first 32 bytes):
c8 a1 c2 27 81 88 ff ff e0 14 a9 c0 ff ff ff ff ...'............
30 1a e1 2e a6 00 00 00 28 fc 5b 17 81 88 ff ff 0.......(.[.....
backtrace:
[<0000000011655661>] kmalloc_trace+0x26/0xa0
[<0000000055f15b82>] virtio_gpu_fence_alloc+0x47/0xc0 [virtio_gpu]
[<00000000fa6d96f9>] virtio_gpu_execbuffer_ioctl+0x1a8/0x800 [virtio_gpu]
[<00000000e6cb5105>] drm_ioctl_kernel+0x169/0x240 [drm]
[<000000005ad33e27>] drm_ioctl+0x399/0x6b0 [drm]
[<00000000a19dbf65>] __x64_sys_ioctl+0xc5/0x100
[<0000000011fa801e>] do_syscall_64+0x5b/0xc0
[<0000000065c76d8a>] entry_SYSCALL_64_after_hwframe+0x6e/0xd8
unreferenced object 0xffff888121930500 (size 128):
comm "kwin_wayland", pid 981, jiffies 4295380313 (age 390.096s)
hex dump (first 32 bytes):
c8 a1 c2 27 81 88 ff ff e0 14 a9 c0 ff ff ff ff ...'............
f9 ec d7 2f a6 00 00 00 28 fc 5b 17 81 88 ff ff .../....(.[.....
backtrace:
[<0000000011655661>] kmalloc_trace+0x26/0xa0
[<0000000055f15b82>] virtio_gpu_fence_alloc+0x47/0xc0 [virtio_gpu]
[<00000000fa6d96f9>] virtio_gpu_execbuffer_ioctl+0x1a8/0x800 [virtio_gpu]
[<00000000e6cb5105>] drm_ioctl_kernel+0x169/0x240 [drm]
[<000000005ad33e27>] drm_ioctl+0x399/0x6b0 [drm]
[<00000000a19dbf65>] __x64_sys_ioctl+0xc5/0x100
[<0000000011fa801e>] do_syscall_64+0x5b/0xc0
[<0000000065c76d8a>] entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[...]

This memleak will grow quickly, being possible to see the
following line in dmesg after few minutes of life in the
virtual machine:

[ 706.217388] kmemleak: 10731 new suspected memory leaks (see /sys/kernel/debug/kmemleak)

The patch will remove the line to allow the cleanup
function do its job.

Signed-off-by: José Pekkarinen <[email protected]>
Fixes: e4812ab8e6b1 ("drm/virtio: Refactor and optimize job submission code path")
Signed-off-by: Dmitry Osipenko <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/virtio: Support sync objects

Add sync object DRM UAPI support to VirtIO-GPU driver. Sync objects
support is needed by native context VirtIO-GPU Mesa drivers, it also will
be used by Venus and Vi

drm/virtio: Support sync objects

Add sync object DRM UAPI support to VirtIO-GPU driver. Sync objects
support is needed by native context VirtIO-GPU Mesa drivers, it also will
be used by Venus and Virgl contexts.

Reviewed-by; Emil Velikov <[email protected]>
Signed-off-by: Dmitry Osipenko <[email protected]>
Tested-by: Pierre-Eric Pelloux-Prayer <[email protected]> # amdgpu nctx
Tested-by: Rob Clark <[email protected]> # freedreno nctx
Reviewed-by: Rob Clark <[email protected]>
Acked-by: Gurchetan Singh <[email protected]>
Acked-by: Gerd Hoffmann <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/virtio: Conditionally allocate virtio_gpu_fence

We don't want to create a fence for every command submission. It's
only necessary when userspace provides a waitable token for submission.
This c

drm/virtio: Conditionally allocate virtio_gpu_fence

We don't want to create a fence for every command submission. It's
only necessary when userspace provides a waitable token for submission.
This could be:

1) bo_handles, to be used with VIRTGPU_WAIT
2) out_fence_fd, to be used with dma_fence apis
3) a ring_idx provided with VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK
+ DRM event API
4) syncobjs in the future

The use case for just submitting a command to the host, and expecting
no response. For example, gfxstream has GFXSTREAM_CONTEXT_PING that
just wakes up the host side worker threads. There's also
CROSS_DOMAIN_CMD_SEND which just sends data to the Wayland server.

This prevents the need to signal the automatically created
virtio_gpu_fence.

In addition, VIRTGPU_EXECBUF_RING_IDX is checked when creating a
DRM event object. VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is
already defined in terms of per-context rings. It was theoretically
possible to create a DRM event on the global timeline (ring_idx == 0),
if the context enabled DRM event polling. However, that wouldn't
work and userspace (Sommelier). Explicitly disallow it for
clarity.

Signed-off-by: Gurchetan Singh <[email protected]>
Reviewed-by: Dmitry Osipenko <[email protected]>
Tested-by: Dmitry Osipenko <[email protected]>
Signed-off-by: Dmitry Osipenko <[email protected]> # edited coding style
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/virtio: Wait for each dma-fence of in-fence array individually

Use dma-fence-unwrap API for waiting each dma-fence of the in-fence array
individually. Sync file's in-fence array always has a non

drm/virtio: Wait for each dma-fence of in-fence array individually

Use dma-fence-unwrap API for waiting each dma-fence of the in-fence array
individually. Sync file's in-fence array always has a non-matching fence
context ID, which doesn't allow to skip waiting of fences with a matching
context ID in a case of a merged sync file fence.

Suggested-by: Rob Clark <[email protected]>
Reviewed-by: Emil Velikov <[email protected]>
Tested-by: Pierre-Eric Pelloux-Prayer <[email protected]>
Signed-off-by: Dmitry Osipenko <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...

drm/virtio: Refactor and optimize job submission code path

Move virtio_gpu_execbuffer_ioctl() into separate virtgpu_submit.c file,
refactoring and optimizing the code along the way to ease addition

drm/virtio: Refactor and optimize job submission code path

Move virtio_gpu_execbuffer_ioctl() into separate virtgpu_submit.c file,
refactoring and optimizing the code along the way to ease addition of new
features to the ioctl.

The optimization is done by using optimal ordering of the job's submission
steps, reducing code path from the start of the ioctl to the point of
pushing job to virtio queue. Job's initialization is now performed before
in-fence is awaited and out-fence setup is made after sending out job to
virtio.

Reviewed-by: Rob Clark <[email protected]>
Reviewed-by: Emil Velikov <[email protected]>
Tested-by: Pierre-Eric Pelloux-Prayer <[email protected]>
Signed-off-by: Dmitry Osipenko <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

show more ...