drm/amdgpu: Fix mqd init on GFX v9.4.3

For MQD init, an XCC's queue is selected with GRBM select. However, for
initialization of MQD, values read from logical XCC0 registers are used.
This results in garbage values being read from XCC0 whose queue is not
selected. Change to read from the right XCC for MQD initialization.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c

@@ -1456,7 +1456,7 @@ static void gfx_v9_4_3_mqd_set_priority(struct amdgpu_ring *ring, struct v9_mqd
 	}
 }
 
-static int gfx_v9_4_3_mqd_init(struct amdgpu_ring *ring)
+static int gfx_v9_4_3_xcc_mqd_init(struct amdgpu_ring *ring, int xcc_id)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct v9_mqd *mqd = ring->mqd_ptr;
@@ -1483,14 +1483,14 @@ static int gfx_v9_4_3_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
 
 	/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
-	tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_HQD_EOP_CONTROL);
+	tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_HQD_EOP_CONTROL);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
 			(order_base_2(GFX9_MEC_HPD_SIZE / 4) - 1));
 
 	mqd->cp_hqd_eop_control = tmp;
 
 	/* enable doorbell? */
-	tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_HQD_PQ_DOORBELL_CONTROL);
+	tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_HQD_PQ_DOORBELL_CONTROL);
 
 	if (ring->use_doorbell) {
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
@@ -1520,7 +1520,7 @@ static int gfx_v9_4_3_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_mqd_base_addr_hi = upper_32_bits(ring->mqd_gpu_addr);
 
 	/* set MQD vmid to 0 */
-	tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_MQD_CONTROL);
+	tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_MQD_CONTROL);
 	tmp = REG_SET_FIELD(tmp, CP_MQD_CONTROL, VMID, 0);
 	mqd->cp_mqd_control = tmp;
 
@@ -1530,7 +1530,7 @@ static int gfx_v9_4_3_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_pq_base_hi = upper_32_bits(hqd_gpu_addr);
 
 	/* set up the HQD, this is similar to CP_RB0_CNTL */
-	tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_HQD_PQ_CONTROL);
+	tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_HQD_PQ_CONTROL);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, QUEUE_SIZE,
 			    (order_base_2(ring->ring_size / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE,
@@ -1557,23 +1557,23 @@ static int gfx_v9_4_3_mqd_init(struct amdgpu_ring *ring)
 
 	/* reset read and write pointers, similar to CP_RB0_WPTR/_RPTR */
 	ring->wptr = 0;
-	mqd->cp_hqd_pq_rptr = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_HQD_PQ_RPTR);
+	mqd->cp_hqd_pq_rptr = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_HQD_PQ_RPTR);
 
 	/* set the vmid for the queue */
 	mqd->cp_hqd_vmid = 0;
 
-	tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_HQD_PERSISTENT_STATE);
+	tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_HQD_PERSISTENT_STATE);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PERSISTENT_STATE, PRELOAD_SIZE, 0x53);
 	mqd->cp_hqd_persistent_state = tmp;
 
 	/* set MIN_IB_AVAIL_SIZE */
-	tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_HQD_IB_CONTROL);
+	tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_HQD_IB_CONTROL);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
 	/* set static priority for a queue/ring */
 	gfx_v9_4_3_mqd_set_priority(ring, mqd);
-	mqd->cp_hqd_quantum = RREG32_SOC15(GC, GET_INST(GC, 0), regCP_HQD_QUANTUM);
+	mqd->cp_hqd_quantum = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_HQD_QUANTUM);
 
 	/* map_queues packet doesn't need activate the queue,
 	 * so only kiq need set this field.
@@ -1771,7 +1771,7 @@ static int gfx_v9_4_3_xcc_kiq_init_queue(struct amdgpu_ring *ring, int xcc_id)
 		((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
 		mutex_lock(&adev->srbm_mutex);
 		soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0, GET_INST(GC, xcc_id));
-		gfx_v9_4_3_mqd_init(ring);
+		gfx_v9_4_3_xcc_mqd_init(ring, xcc_id);
 		gfx_v9_4_3_xcc_kiq_init_register(ring, xcc_id);
 		soc15_grbm_select(adev, 0, 0, 0, 0, GET_INST(GC, xcc_id));
 		mutex_unlock(&adev->srbm_mutex);
@@ -1802,7 +1802,7 @@ static int gfx_v9_4_3_xcc_kcq_init_queue(struct amdgpu_ring *ring, int xcc_id)
 		((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
 		mutex_lock(&adev->srbm_mutex);
 		soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0, GET_INST(GC, xcc_id));
-		gfx_v9_4_3_mqd_init(ring);
+		gfx_v9_4_3_xcc_mqd_init(ring, xcc_id);
 		soc15_grbm_select(adev, 0, 0, 0, 0, GET_INST(GC, xcc_id));
 		mutex_unlock(&adev->srbm_mutex);