+ *
+ * The rdma core library can map doorbell register in two ways,
+ * depending on the environment variable "MLX5_SHUT_UP_BF":
+ *
+ * - as regular cached memory, the variable is either missing or
+ * set to zero. This type of mapping may cause the significant
+ * doorbell register writing latency and requires explicit
+ * memory write barrier to mitigate this issue and prevent
+ * write combining.
+ *
+ * - as non-cached memory, the variable is present and set to
+ * not "0" value. This type of mapping may cause performance
+ * impact under heavy loading conditions but the explicit write
+ * memory barrier is not required and it may improve core
+ * performance.
+ *
+ * - the legacy behaviour (prior 19.08 release) was to use some
+ * heuristics to decide whether write memory barrier should
+ * be performed. This behavior is supported with specifying
+ * tx_db_nc=2, write barrier is skipped if application
+ * provides the full recommended burst of packets, it
+ * supposes the next packets are coming and the write barrier
+ * will be issued on the next burst (after descriptor writing,
+ * at least).