@@ -614,13 +614,29 @@ print_dpdk_version(void)
puts(rte_version());
}
+/* Avoid calling rte_cpu_get_flag_enabled() excessively, by caching the
+ * result of the call for each CPU flag in a static variable. To avoid
+ * allocating large numbers of static variables, use a uint8 as a bitfield.
+ * Note the macro must only return if the ISA check done and is available.
+ */
+#define ISA_CHECK_DONE_BIT (1 << 0)
+#define ISA_AVAILABLE_BIT (1 << 1)
+
#define CHECK_CPU_FEATURE(feature, name_str, RTE_CPUFLAG) \
do { \
if (strncmp(feature, name_str, strlen(name_str)) == 0) { \
- int has_isa = rte_cpu_get_flag_enabled(RTE_CPUFLAG); \
- VLOG_DBG("CPU flag %s, available %s\n", name_str, \
- has_isa ? "yes" : "no"); \
- return true; \
+ static uint8_t isa_check_##RTE_CPUFLAG; \
+ int check = isa_check_##RTE_CPUFLAG & ISA_CHECK_DONE_BIT; \
+ if (OVS_UNLIKELY(!check)) { \
+ int has_isa = rte_cpu_get_flag_enabled(RTE_CPUFLAG); \
+ VLOG_DBG("CPU flag %s, available %s\n", \
+ name_str, has_isa ? "yes" : "no"); \
+ isa_check_##RTE_CPUFLAG = ISA_CHECK_DONE_BIT; \
+ if (has_isa) \
+ isa_check_##RTE_CPUFLAG |= ISA_AVAILABLE_BIT; \
+ } \
+ if (isa_check_##RTE_CPUFLAG & ISA_AVAILABLE_BIT) \
+ return true; \
} \
} while (0)
As a small optimization, this patch caches the result of a CPU ISA check from DPDK. Particularly in the case of running the DPCLS autovalidator (which repeatedly probes subtables) this reduces the amount of CPU ISA lookups from the DPDK level. By caching them at the OVS/dpdk.c level, the ISA checks remain runtime for the CPU where they are executed, but subsequent checks for the same ISA feature become much cheaper. Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com> --- In theory it is also possible to do the caching of the supported ISA at the usage site (aka, the DPCLS subtable search implementation) however that would cause a lot of code-duplication. By caching in the lower level, we get almost all the benefit with no code duplication. --- lib/dpdk.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-)