[dpdk-dev] [RFC 1/3] Replace lrand48-based rte_rand with LFSR generator

[Mattias Rönnblom]

This commit replaces rte_rand()'s use of lrand48() with a DPDK-native
combined Linear Feedback Shift Register (LFSR) (also known as
Tausworthe) pseudo-number generator, with four sequences.

This generator is faster and produces better quality random numbers
than libc's lrand48() implementation. This implementation, as opposed
to lrand48(), is multi-thread safe in regards to concurrent rte_rand()
calls from different lcore threads.

Signed-off-by: Mattias Rönnblom <mattias.ronnblom at ericsson.com>
---
 lib/librte_eal/common/include/rte_random.h |  25 ++---
 lib/librte_eal/common/meson.build          |   1 +
 lib/librte_eal/common/rte_random.c         | 104 +++++++++++++++++++++
 lib/librte_eal/freebsd/eal/Makefile        |   1 +
 lib/librte_eal/freebsd/eal/eal.c           |   2 -
 lib/librte_eal/linux/eal/Makefile          |   1 +
 lib/librte_eal/linux/eal/eal.c             |   2 -
 lib/librte_eal/rte_eal_version.map         |   2 +
 8 files changed, 119 insertions(+), 19 deletions(-)
 create mode 100644 lib/librte_eal/common/rte_random.c

diff --git a/lib/librte_eal/common/include/rte_random.h b/lib/librte_eal/common/include/rte_random.h
index b2ca1c209..bca85a672 100644
--- a/lib/librte_eal/common/include/rte_random.h
+++ b/lib/librte_eal/common/include/rte_random.h
@@ -16,7 +16,6 @@ extern "C" {
 #endif
 
 #include <stdint.h>
-#include <stdlib.h>
 
 /**
  * Seed the pseudo-random generator.
@@ -25,14 +24,15 @@ extern "C" {
  * value. It may need to be re-seeded by the user with a real random
  * value.
  *
+ * This function is not multi-thread safe in regards to other
+ * rte_srand() calls, nor is it in relation to concurrent rte_rand()
+ * calls.
+ *
  * @param seedval
  *   The value of the seed.
  */
-static inline void
-rte_srand(uint64_t seedval)
-{
-	srand48((long)seedval);
-}
+void
+rte_srand(uint64_t seedval);
 
 /**
  * Get a pseudo-random value.
@@ -41,18 +41,13 @@ rte_srand(uint64_t seedval)
  * congruential algorithm and 48-bit integer arithmetic, called twice
  * to generate a 64-bit value.
  *
+ * If called from lcore threads, this function is thread-safe.
+ *
  * @return
  *   A pseudo-random value between 0 and (1<<64)-1.
  */
-static inline uint64_t
-rte_rand(void)
-{
-	uint64_t val;
-	val = (uint64_t)lrand48();
-	val <<= 32;
-	val += (uint64_t)lrand48();
-	return val;
-}
+uint64_t
+rte_rand(void);
 
 #ifdef __cplusplus
 }
diff --git a/lib/librte_eal/common/meson.build b/lib/librte_eal/common/meson.build
index 0670e4102..bafd23207 100644
--- a/lib/librte_eal/common/meson.build
+++ b/lib/librte_eal/common/meson.build
@@ -35,6 +35,7 @@ common_sources = files(
 	'rte_keepalive.c',
 	'rte_malloc.c',
 	'rte_option.c',
+	'rte_random.c',
 	'rte_reciprocal.c',
 	'rte_service.c'
 )
diff --git a/lib/librte_eal/common/rte_random.c b/lib/librte_eal/common/rte_random.c
new file mode 100644
index 000000000..b8fb7006e
--- /dev/null
+++ b/lib/librte_eal/common/rte_random.c
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Ericsson AB
+ */
+
+#include <stdlib.h>
+
+#include <rte_cycles.h>
+#include <rte_eal.h>
+#include <rte_lcore.h>
+#include <rte_random.h>
+
+struct rte_rand_state {
+	uint32_t z1;
+	uint32_t z2;
+	uint32_t z3;
+	uint32_t z4;
+} __rte_cache_aligned;
+
+static struct rte_rand_state rand_states[RTE_MAX_LCORE];
+
+static inline uint32_t
+__rte_rand_lcg32(uint32_t *seed)
+{
+	*seed = 1103515245U * *seed + 12345;
+	return *seed;
+}
+
+static uint32_t
+__rte_rand_lfsr113_gen_seed(uint32_t *seed, uint32_t min_value)
+{
+	uint32_t res = __rte_rand_lcg32(seed);
+
+	return res < min_value ? res + min_value : res;
+}
+
+static void
+__rte_srand_lfsr113(uint32_t seed, struct rte_rand_state *state)
+{
+	uint32_t lcg32_seed = seed;
+	state->z1 = __rte_rand_lfsr113_gen_seed(&lcg32_seed, 2U);
+	state->z2 = __rte_rand_lfsr113_gen_seed(&lcg32_seed, 8U);
+	state->z3 = __rte_rand_lfsr113_gen_seed(&lcg32_seed, 16U);
+	state->z4 = __rte_rand_lfsr113_gen_seed(&lcg32_seed, 128U);
+}
+
+void __rte_experimental
+rte_srand(uint64_t seedval)
+{
+	unsigned int lcore_id;
+
+	/* add lcore_id to seed to avoid having the same sequence */
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
+		__rte_srand_lfsr113(seedval + lcore_id, &rand_states[lcore_id]);
+}
+
+static __rte_always_inline uint32_t
+__rte_rand_lfsr113(uint32_t s, uint32_t a, uint32_t b, uint32_t c,  uint32_t d)
+{
+	return ((s & c) << d) ^ (((s << a) ^ s) >> b);
+}
+
+static __rte_always_inline uint32_t
+__rte_rand32(struct rte_rand_state *state)
+{
+	state->z1 = __rte_rand_lfsr113(state->z1, 6U, 13U, 4294967294U, 18U);
+	state->z2 = __rte_rand_lfsr113(state->z2, 2U, 27U, 4294967288U, 2U);
+	state->z3 = __rte_rand_lfsr113(state->z3, 13U, 21U, 4294967280U, 7U);
+	state->z4 = __rte_rand_lfsr113(state->z4, 3U, 12U, 4294967168U, 13U);
+
+	return state->z1 ^ state->z2 ^ state->z3 ^ state->z4;
+}
+
+static __rte_always_inline
+struct rte_rand_state *__rte_rand_get_state(void)
+{
+	unsigned int lcore_id;
+
+	lcore_id = rte_lcore_id();
+
+	if (unlikely(lcore_id == LCORE_ID_ANY))
+		lcore_id = rte_get_master_lcore();
+
+	return &rand_states[lcore_id];
+}
+
+uint64_t __rte_experimental
+rte_rand(void)
+{
+	struct rte_rand_state *state;
+	uint64_t low;
+	uint64_t high;
+
+	state = __rte_rand_get_state();
+
+	low = __rte_rand32(state);
+	high = __rte_rand32(state);
+
+	return low | (high << 32);
+}
+
+RTE_INIT(rte_rand_init)
+{
+	rte_srand(rte_get_timer_cycles());
+}
diff --git a/lib/librte_eal/freebsd/eal/Makefile b/lib/librte_eal/freebsd/eal/Makefile
index 19854ee2c..ca616c480 100644
--- a/lib/librte_eal/freebsd/eal/Makefile
+++ b/lib/librte_eal/freebsd/eal/Makefile
@@ -69,6 +69,7 @@ SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += malloc_mp.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_keepalive.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_option.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_service.c
+SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_random.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_reciprocal.c
 
 # from arch dir
diff --git a/lib/librte_eal/freebsd/eal/eal.c b/lib/librte_eal/freebsd/eal/eal.c
index c6ac9028f..5d43310b3 100644
--- a/lib/librte_eal/freebsd/eal/eal.c
+++ b/lib/librte_eal/freebsd/eal/eal.c
@@ -727,8 +727,6 @@ rte_eal_init(int argc, char **argv)
 #endif
 	}
 
-	rte_srand(rte_rdtsc());
-
 	/* in secondary processes, memory init may allocate additional fbarrays
 	 * not present in primary processes, so to avoid any potential issues,
 	 * initialize memzones first.
diff --git a/lib/librte_eal/linux/eal/Makefile b/lib/librte_eal/linux/eal/Makefile
index 6e5261152..729795a10 100644
--- a/lib/librte_eal/linux/eal/Makefile
+++ b/lib/librte_eal/linux/eal/Makefile
@@ -77,6 +77,7 @@ SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += malloc_mp.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_keepalive.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_option.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_service.c
+SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_random.c
 SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_reciprocal.c
 
 # from arch dir
diff --git a/lib/librte_eal/linux/eal/eal.c b/lib/librte_eal/linux/eal/eal.c
index f7ae62d7b..c2bdf0a67 100644
--- a/lib/librte_eal/linux/eal/eal.c
+++ b/lib/librte_eal/linux/eal/eal.c
@@ -1083,8 +1083,6 @@ rte_eal_init(int argc, char **argv)
 #endif
 	}
 
-	rte_srand(rte_rdtsc());
-
 	if (rte_eal_log_init(logid, internal_config.syslog_facility) < 0) {
 		rte_eal_init_alert("Cannot init logging.");
 		rte_errno = ENOMEM;
diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index d6e375135..0d60668fa 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -366,10 +366,12 @@ EXPERIMENTAL {
 	rte_mp_request_async;
 	rte_mp_sendmsg;
 	rte_option_register;
+	rte_rand;
 	rte_realloc_socket;
 	rte_service_lcore_attr_get;
 	rte_service_lcore_attr_reset_all;
 	rte_service_may_be_active;
 	rte_socket_count;
 	rte_socket_id_by_idx;
+	rte_srand;
 };
-- 
2.17.1