There is a possibility that some waves in an NGG workgroup
don't have any input vertices, only primitives. When these
waves store the primitive ID as a per-primitive attribute,
they will need to wait for those stores before the primitive
export, because the other waves can't wait for them.
Cc: mesa-stable
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33218>
This case is unlikely but possible. We forgot to handle it here,
because it was originally handled by the backend compiler.
On GFX10 chips that have issues with 0 vertices and primitives
exported, this will always export at least 1 vertex and primitive.
This could theoretically fix some hangs on Navi 10, although we are not aware of a specific issue caused by this problem.
Cc: mesa-stable
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33218>
Using the used component count is not enough. We need to consider
the component mask because any component can be disabled. This might
fix tests.
This removes the component counting from ac_get_fs_input_vgpr_cnt
and determines the component mask where it's needed.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32910>
This returns the underlying device pointer but as an opaque
uintptr_t.
This will be required because libdrm_amdgpu will return the
same device when called multiple times from the same process.
radeonsi relies on the pointer value to identify if the device
are the same and adjust the synchronisation logic based on that.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33081>
Determine whether the device has hardware raytracing support early, and
then use this result where needed, instead of checking for `gfx_level`
every time.
This is a prerequisite for CYAN_SKILLFISH chip enablement. This chip is
still GFX10, not GFX10_3, but has hardware support for accelerated
`image_bvh{,64}_intersect_ray` instructions. Just checking for `gfx_level`
is insufficient for it.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33109>
On the host side virglrenderer creates dmabuf on demand when:
* cpu mapping is requested
* setting up scan out
* sharing buffers between guest processes
On-demand dmabuf creation only works if the ctx that created the
BO still exists and knows about this BO. This assumption works ok for
the first 2 cases, but can break with the last one (and it does cause
issues on Android). eg:
* process A allocates BO and exports it as a guest dmabuf
* process A closes its handle to the BO (-> detach_resource)
* process B imports the guest dmabuf -> this triggers the attach_resource
function in virglrenderer. If the given resource isn't a
VIRGL_RESOURCE_FD_DMABUF it'll try to get one... But for this to work,
process A needs to be used -> this fails because this resource was
detached from it.
The reason we create dmabuf on demand is to avoid hitting the number of
open file descriptor limit. So to cover the 3rd case, we'll use the
VIRTGPU_BLOB_FLAG_USE_SHAREABLE flag, but try to limit to as few possible
buffers as possible.
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21658>
Native context support is implemented by diverting the libdrm_amdgpu functions
into new functions that use virtio-gpu.
VA allocations are done directly in the guest, using newly exposed libdrm_amdgpu
helpers (retrieved through dlopen/dlsym).
Guest <-> Host roundtrips can be expensive so we try to avoid them as much as
possible. When possible we also don't wait for the host reply in case where
it's not needed to get correct result.
Implicit sync works because virtio-gpu commands are submitted in order to the
host (there a single queue per device, shared by all the guest processes).
virtio-gpu also only supports one context per file description (but multiple
file descriptions per process) while amdgpu only allows one fd per process,
but multiple contexts per fd. This causes synchronization problems, because
virtio-gpu drops all sync primitive if they belong to the same fd/context/ring:
ie the amdgpu_ctx can't be expressed in virtio-gpu terms.
For now the solution is to only allocate a single amdgpu_ctx per application.
Contrary to radeonsi/radv, amdgpu_virtio can use libdrm_amdgpu directly: the
ones that don't rely on ioctl() are safe to use here.
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21658>
This is required to implement virtio native-context.
In a virtualized environment, most of the functions provided
by libdrm_amdgpu will be implemented using virtio.
This allows to implement efficient virtualization, by
forwarding the kernel API to the host, instead of the GL/VK calls.
Similarly, the raw 'fd' or 'gem_handle' arguments are replaced
by opaque types. This allows to encapsulate all the needed
state in the handle, and use unmodified API between baremetal
and virtualized contexts.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21658>
