The assertion considers max_dw from the current IB in the chain, but
big_ib_buffer is a buffer for the next IB, which can be smaller.
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Acked-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
va = amdgpu_winsys_bo(ib->big_ib_buffer)->va;
/* This space was originally reserved. */
- rcs->current.max_dw += 4;
- assert(ib->used_ib_space + 4 * rcs->current.max_dw <= ib->big_ib_buffer->size);
+ rcs->current.max_dw += cs_epilog_dw;
/* Pad with NOPs and add INDIRECT_BUFFER packet */
while ((rcs->current.cdw & 7) != 4)