Commen=
t # 7
on bug 10511=
3
from Jan Vesely
(In reply to Maciej S. Szmigiero from comment #6)
> There are really two issues at play here:
> 1) If the LLVM-generated code cannot be run properly then it should be=
simply
> rejected by whatever is actually in charge of submitting it to the GPU=
(I
> guess
> this would be Mesa?).
> This way an application will know it cannot use OpenCL for computation=
, at
> least
> not with this compute kernel.
>=20
> Instead, it currently looks like many of these test run but give incor=
rect
> results, which is obviously rather bad.
Do you have an example of this? clover should return OUT_OF_RESOURCES error
when the compute state creation fails (like in the presence of code
relocations).
It does not change the content of the buffer, so it will return whatever was
stored in the buffer on creation.
> 2) Some (previous) Mesa + LLVM versions generate=
a command stream that
> crashes the GPU and, as far as I can remember, sometimes even lockup t=
he
> whole machine.
>=20
> It should not be possible to crash the GPU, regardless how incorrect a
> command stream that userspace sends to it is - because otherwise it is
> possible for
> an unprivileged user with GPU access to DoS the machine.
This is a separate issue. GPU hangs are generally addressed via gpu reset w=
hich
should be enabled for gfx8/9 GPUs in recent amdgpu.ko [0]
[0] https://pat=
chwork.freedesktop.org/patch/257994/