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

As MES requires per context preemption, use per context CSA address
for DE metadata to correctly enable context MCBP preemption.
Signed-off-by: NJack Xiao <Jack.Xiao@amd.com>
Acked-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -8889,12 +8889,33 @@ static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct v10_de_ib_state de_payload = {0};
-	uint64_t csa_addr, gds_addr;
+	uint64_t offset, gds_addr, de_payload_gpu_addr;
+	void *de_payload_cpu_addr;
 	int cnt;
 
-	csa_addr = amdgpu_csa_vaddr(ring->adev);
-	gds_addr = ALIGN(csa_addr + AMDGPU_CSA_SIZE - adev->gds.gds_size,
-			 PAGE_SIZE);
+	if (ring->is_mes_queue) {
+		offset = offsetof(struct amdgpu_mes_ctx_meta_data,
+				  gfx[0].gfx_meta_data) +
+			offsetof(struct v10_gfx_meta_data, de_payload);
+		de_payload_gpu_addr =
+			amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
+		de_payload_cpu_addr =
+			amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset);
+
+		offset = offsetof(struct amdgpu_mes_ctx_meta_data,
+				  gfx[0].gds_backup) +
+			offsetof(struct v10_gfx_meta_data, de_payload);
+		gds_addr = amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
+	} else {
+		offset = offsetof(struct v10_gfx_meta_data, de_payload);
+		de_payload_gpu_addr = amdgpu_csa_vaddr(ring->adev) + offset;
+		de_payload_cpu_addr = adev->virt.csa_cpu_addr + offset;
+
+		gds_addr = ALIGN(amdgpu_csa_vaddr(ring->adev) +
+				 AMDGPU_CSA_SIZE - adev->gds.gds_size,
+				 PAGE_SIZE);
+	}
+
 	de_payload.gds_backup_addrlo = lower_32_bits(gds_addr);
 	de_payload.gds_backup_addrhi = upper_32_bits(gds_addr);
 
@@ -8904,15 +8925,11 @@ static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume)
 				 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, de_payload)));
-	amdgpu_ring_write(ring, upper_32_bits(csa_addr +
-			      offsetof(struct v10_gfx_meta_data, de_payload)));
+	amdgpu_ring_write(ring, lower_32_bits(de_payload_gpu_addr));
+	amdgpu_ring_write(ring, upper_32_bits(de_payload_gpu_addr));
 
 	if (resume)
-		amdgpu_ring_write_multiple(ring, adev->virt.csa_cpu_addr +
-					   offsetof(struct v10_gfx_meta_data,
-						    de_payload),
+		amdgpu_ring_write_multiple(ring, de_payload_cpu_addr,
 					   sizeof(de_payload) >> 2);
 	else
 		amdgpu_ring_write_multiple(ring, (void *)&de_payload,