diff --git a/src/broadcom/common/v3d_limits.h b/src/broadcom/common/v3d_limits.h
index 755aedd787c..492740c44f9 100644
--- a/src/broadcom/common/v3d_limits.h
+++ b/src/broadcom/common/v3d_limits.h
@@ -24,6 +24,8 @@
 #ifndef V3D_LIMITS_H
 #define V3D_LIMITS_H
 
+#define V3D_CL_MAX_INSTR_SIZE 25
+
 /* Number of channels a QPU thread executes in parallel.  Also known as
  * gl_SubGroupSizeARB.
  */
diff --git a/src/broadcom/vulkan/v3dv_cl.c b/src/broadcom/vulkan/v3dv_cl.c
index fab9b05ec48..acdd013a996 100644
--- a/src/broadcom/vulkan/v3dv_cl.c
+++ b/src/broadcom/vulkan/v3dv_cl.c
@@ -122,14 +122,18 @@ v3dv_cl_ensure_space_with_branch(struct v3dv_cl *cl, uint32_t space)
     * end with a 'return from sub list' command.
     */
    bool needs_return_from_sub_list = false;
-   if (cl->job->type == V3DV_JOB_TYPE_GPU_CL_SECONDARY) {
-      if (cl->size > 0) {
+   if (cl->job->type == V3DV_JOB_TYPE_GPU_CL_SECONDARY && cl->size > 0)
          needs_return_from_sub_list = true;
-         space += cl_packet_length(RETURN_FROM_SUB_LIST);
-      }
-   } else {
-      space += cl_packet_length(BRANCH);
-   }
+
+   /*
+    * The CLE processor in the simulator tries to read V3D_CL_MAX_INSTR_SIZE
+    * bytes form the CL for each new instruction. If the last instruction in our
+    * CL is smaller than that, and there are not at least V3D_CL_MAX_INSTR_SIZE
+    * bytes until the end of the BO, it will read out of bounds and possibly
+    * cause a GMP violation interrupt to trigger. Ensure we always have at
+    * least that many bytes available to read with the last instruction.
+    */
+   space += V3D_CL_MAX_INSTR_SIZE;
 
    if (v3dv_cl_offset(cl) + space <= cl->size)
       return;