(order_base_2(prop->queue_size / 4) - 1));
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
(order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
- tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0);
+ tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
m->cp_hqd_pq_control |=
ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
+ m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);