drm/amdgpu: implement sdma_v4_0_ring_emit_reg_wait

Add emit_reg_wait implementation for SDMA v4.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c

@@ -1152,6 +1152,20 @@ static void sdma_v4_0_ring_emit_wreg(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, val);
 }
 
+static void sdma_v4_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+					 uint32_t val, uint32_t mask)
+{
+	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
+			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(0) |
+			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* equal */
+	amdgpu_ring_write(ring, reg << 2);
+	amdgpu_ring_write(ring, 0);
+	amdgpu_ring_write(ring, val); /* reference */
+	amdgpu_ring_write(ring, mask); /* mask */
+	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
+			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10));
+}
+
 static int sdma_v4_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1588,6 +1602,7 @@ static const struct amdgpu_ring_funcs sdma_v4_0_ring_funcs = {
 	.insert_nop = sdma_v4_0_ring_insert_nop,
 	.pad_ib = sdma_v4_0_ring_pad_ib,
 	.emit_wreg = sdma_v4_0_ring_emit_wreg,
+	.emit_reg_wait = sdma_v4_0_ring_emit_reg_wait,
 };
 
 static void sdma_v4_0_set_ring_funcs(struct amdgpu_device *adev)