drm/amdgpu/gfx10: use per ctx CSA for ce metadata

As MES requires per context preemption, use per context CSA address
for CE metadata to correctly enable context MCBP preemption.
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Acked-by: Christian König <christian.koenig@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_v10_0.c

@@ -8849,26 +8849,36 @@ static void gfx_v10_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct v10_ce_ib_state ce_payload = {0};
-	uint64_t csa_addr;
+	uint64_t offset, ce_payload_gpu_addr;
+	void *ce_payload_cpu_addr;
 	int cnt;
 
 	cnt = (sizeof(ce_payload) >> 2) + 4 - 2;
-	csa_addr = amdgpu_csa_vaddr(ring->adev);
+
+	if (ring->is_mes_queue) {
+		offset = offsetof(struct amdgpu_mes_ctx_meta_data,
+				  gfx[0].gfx_meta_data) +
+			offsetof(struct v10_gfx_meta_data, ce_payload);
+		ce_payload_gpu_addr =
+			amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
+		ce_payload_cpu_addr =
+			amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset);
+	} else {
+		offset = offsetof(struct v10_gfx_meta_data, ce_payload);
+		ce_payload_gpu_addr = amdgpu_csa_vaddr(ring->adev) + offset;
+		ce_payload_cpu_addr = adev->virt.csa_cpu_addr + offset;
+	}
 
 	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, cnt));
 	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(2) |
 				 WRITE_DATA_DST_SEL(8) |
 				 WR_CONFIRM) |
 				 WRITE_DATA_CACHE_POLICY(0));
-	amdgpu_ring_write(ring, lower_32_bits(csa_addr +
-			      offsetof(struct v10_gfx_meta_data, ce_payload)));
-	amdgpu_ring_write(ring, upper_32_bits(csa_addr +
-			      offsetof(struct v10_gfx_meta_data, ce_payload)));
+	amdgpu_ring_write(ring, lower_32_bits(ce_payload_gpu_addr));
+	amdgpu_ring_write(ring, upper_32_bits(ce_payload_gpu_addr));
 
 	if (resume)
-		amdgpu_ring_write_multiple(ring, adev->virt.csa_cpu_addr +
-					   offsetof(struct v10_gfx_meta_data,
-						    ce_payload),
+		amdgpu_ring_write_multiple(ring, ce_payload_cpu_addr,
 					   sizeof(ce_payload) >> 2);
 	else
 		amdgpu_ring_write_multiple(ring, (void *)&ce_payload,