drm/amdgpu:insert TMZ_BEGIN

FRAME_CONTROL(begin) is needed for vega10 due to ucode logic change,
it can fix some CTS random fail under gfx preemption enabled mode.
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -3764,6 +3764,12 @@ static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring)
 	amdgpu_ring_write_multiple(ring, (void *)&de_payload, sizeof(de_payload) >> 2);
 }
 
+static void gfx_v9_0_ring_emit_tmz(struct amdgpu_ring *ring, bool start)
+{
+	amdgpu_ring_write(ring, PACKET3(PACKET3_FRAME_CONTROL, 0));
+	amdgpu_ring_write(ring, FRAME_CMD(start ? 0 : 1)); /* frame_end */
+}
+
 static void gfx_v9_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)
 {
 	uint32_t dw2 = 0;
@@ -3771,6 +3777,8 @@ static void gfx_v9_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)
 	if (amdgpu_sriov_vf(ring->adev))
 		gfx_v9_0_ring_emit_ce_meta(ring);
 
+	gfx_v9_0_ring_emit_tmz(ring, true);
+
 	dw2 |= 0x80000000; /* set load_enable otherwise this package is just NOPs */
 	if (flags & AMDGPU_HAVE_CTX_SWITCH) {
 		/* set load_global_config & load_global_uconfig */
@@ -3821,12 +3829,6 @@ static void gfx_v9_0_ring_emit_patch_cond_exec(struct amdgpu_ring *ring, unsigne
 		ring->ring[offset] = (ring->ring_size>>2) - offset + cur;
 }
 
-static void gfx_v9_0_ring_emit_tmz(struct amdgpu_ring *ring, bool start)
-{
-	amdgpu_ring_write(ring, PACKET3(PACKET3_FRAME_CONTROL, 0));
-	amdgpu_ring_write(ring, FRAME_CMD(start ? 0 : 1)); /* frame_end */
-}
-
 static void gfx_v9_0_ring_emit_rreg(struct amdgpu_ring *ring, uint32_t reg)
 {
 	struct amdgpu_device *adev = ring->adev;