On Tue, Apr 20, 2021 at 04:34:18PM +0800, Christian König wrote: > Am 20.04.21 um 10:27 schrieb Jinzhou Su: > > The buffer of SA bo will be used by many cases. So better > > to flush the cache of indirect buffer allocated by SA before > > commit the IB. > > > > Signed-off-by: Jinzhou Su <Jinzhou.Su@xxxxxxx> > > --- > > drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 2 ++ > > 1 file changed, 2 insertions(+) > > > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c > > index 148a3b481b12..a2fe2dac32c1 100644 > > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c > > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c > > @@ -76,6 +76,8 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm, > > } > > > > ib->ptr = amdgpu_sa_bo_cpu_addr(ib->sa_bo); > > + /* flush the cache before commit the IB */ > > Either drop the comment or change it a bit. > > E.g. like "/* Invalidate the cache to make the GPU see the newest SA > content */ > > With that done the patch is Reviewed-by: Christian König > <christian.koenig@xxxxxxx> Yes, with this fix, patch looks good for me as well. Reviewed-by: Huang Rui <ray.huang@xxxxxxx> > > Regards, > Christian. > > > + ib->flags = AMDGPU_IB_FLAG_EMIT_MEM_SYNC; > > > > if (!vm) > > ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo); > _______________________________________________ amd-gfx mailing list amd-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/amd-gfx
