[RFC v2 6/6] eal: add unit tests for atomic bit access functions

["Mattias Rönnblom" <mattias.ronnblom@ericsson.com>]

Extend bitops tests to cover the
rte_bit_atomic_[set|clear|assign|test|test_and_[set|clear|assign]]()
family of functions.

Signed-off-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
---
 app/test/test_bitops.c       | 233 ++++++++++++++++++++++++++++++++++-
 lib/eal/include/rte_bitops.h |   1 -
 2 files changed, 232 insertions(+), 2 deletions(-)

diff --git a/app/test/test_bitops.c b/app/test/test_bitops.c
index 12c1027e36..a0967260aa 100644
--- a/app/test/test_bitops.c
+++ b/app/test/test_bitops.c
@@ -3,10 +3,13 @@
  * Copyright(c) 2024 Ericsson AB
  */
 
+#include <inttypes.h>
 #include <stdbool.h>
 
-#include <rte_launch.h>
 #include <rte_bitops.h>
+#include <rte_cycles.h>
+#include <rte_launch.h>
+#include <rte_lcore.h>
 #include <rte_random.h>
 #include "test.h"
 
@@ -60,6 +63,228 @@ GEN_TEST_BIT_ACCESS(test_bit_once_access_64, rte_bit_once_set,		\
 		    rte_bit_once_clear, rte_bit_once_assign,		\
 		    rte_bit_once_test, 64)
 
+#define bit_atomic_set(addr, nr)				\
+	rte_bit_atomic_set(addr, nr, rte_memory_order_relaxed)
+
+#define bit_atomic_clear(addr, nr)					\
+	rte_bit_atomic_clear(addr, nr, rte_memory_order_relaxed)
+
+#define bit_atomic_assign(addr, nr, value)				\
+	rte_bit_atomic_assign(addr, nr, value, rte_memory_order_relaxed)
+
+#define bit_atomic_test(addr, nr)				\
+	rte_bit_atomic_test(addr, nr, rte_memory_order_relaxed)
+
+GEN_TEST_BIT_ACCESS(test_bit_atomic_access_32, bit_atomic_set,	\
+		    bit_atomic_clear, bit_atomic_assign,	\
+		    bit_atomic_test, 32)
+
+GEN_TEST_BIT_ACCESS(test_bit_atomic_access_64, bit_atomic_set,	\
+		    bit_atomic_clear, bit_atomic_assign,	\
+		    bit_atomic_test, 64)
+
+#define PARALLEL_TEST_RUNTIME 0.25
+
+#define GEN_TEST_BIT_PARALLEL_ASSIGN(size)				\
+									\
+	struct parallel_access_lcore_ ## size				\
+	{								\
+		unsigned int bit;					\
+		uint ## size ##_t *word;				\
+		bool failed;						\
+	};								\
+									\
+	static int							\
+	run_parallel_assign_ ## size(void *arg)				\
+	{								\
+		struct parallel_access_lcore_ ## size *lcore = arg;	\
+		uint64_t deadline = rte_get_timer_cycles() +		\
+			PARALLEL_TEST_RUNTIME * rte_get_timer_hz();	\
+		bool value = false;					\
+									\
+		do {							\
+			bool new_value = rte_rand() & 1;		\
+			bool use_test_and_modify = rte_rand() & 1;	\
+			bool use_assign = rte_rand() & 1;		\
+									\
+			if (rte_bit_atomic_test(lcore->word, lcore->bit, \
+						rte_memory_order_relaxed) != value) { \
+				lcore->failed = true;			\
+				break;					\
+			}						\
+									\
+			if (use_test_and_modify) {			\
+				bool old_value;				\
+				if (use_assign) 			\
+					old_value = rte_bit_atomic_test_and_assign( \
+						lcore->word, lcore->bit, new_value, \
+						rte_memory_order_relaxed); \
+				else {					\
+					old_value = new_value ?		\
+						rte_bit_atomic_test_and_set( \
+							lcore->word, lcore->bit, \
+							rte_memory_order_relaxed) : \
+						rte_bit_atomic_test_and_clear( \
+							lcore->word, lcore->bit, \
+							rte_memory_order_relaxed); \
+				}					\
+				if (old_value != value) {		\
+					lcore->failed = true;		\
+					break;				\
+				}					\
+			} else {					\
+				if (use_assign)				\
+					rte_bit_atomic_assign(lcore->word, lcore->bit, \
+							      new_value, \
+							      rte_memory_order_relaxed); \
+				else {					\
+					if (new_value)			\
+						rte_bit_atomic_set(	\
+							lcore->word, lcore->bit, \
+							rte_memory_order_relaxed); \
+					else				\
+						rte_bit_atomic_clear(	\
+							lcore->word, lcore->bit, \
+							rte_memory_order_relaxed); \
+				}					\
+			}						\
+									\
+			value = new_value;				\
+		} while (rte_get_timer_cycles() < deadline);		\
+									\
+		return 0;						\
+	}								\
+									\
+	static int							\
+	test_bit_atomic_parallel_assign_ ## size(void)			\
+	{								\
+		unsigned int worker_lcore_id;				\
+		uint ## size ## _t word = 0;				\
+		struct parallel_access_lcore_ ## size main = {		\
+			.word = &word					\
+		};							\
+		struct parallel_access_lcore_ ## size worker = {	\
+			.word = &word					\
+		};							\
+									\
+		if (rte_lcore_count() < 2) {				\
+			printf("Need multiple cores to run parallel test.\n"); \
+			return TEST_SKIPPED;				\
+		}							\
+									\
+		worker_lcore_id = rte_get_next_lcore(-1, 1, 0);		\
+									\
+		main.bit = rte_rand_max(size);				\
+		do {							\
+			worker.bit = rte_rand_max(size);		\
+		} while (worker.bit == main.bit);			\
+									\
+		int rc = rte_eal_remote_launch(run_parallel_assign_ ## size, \
+					       &worker,	worker_lcore_id); \
+		TEST_ASSERT(rc == 0, "Worker thread launch failed");	\
+									\
+		run_parallel_assign_ ## size(&main);			\
+									\
+		rte_eal_mp_wait_lcore();				\
+									\
+		TEST_ASSERT(!main.failed, "Main lcore atomic access failed"); \
+		TEST_ASSERT(!worker.failed, "Worker lcore atomic access " \
+			    "failed");					\
+									\
+		return TEST_SUCCESS;					\
+	}
+
+GEN_TEST_BIT_PARALLEL_ASSIGN(32)
+GEN_TEST_BIT_PARALLEL_ASSIGN(64)
+
+#define GEN_TEST_BIT_PARALLEL_TEST_AND_MODIFY(size)			\
+									\
+	struct parallel_test_and_set_lcore_ ## size			\
+	{								\
+		uint ## size ##_t *word;				\
+		unsigned int bit;					\
+		uint64_t flips;						\
+	};								\
+									\
+	static int							\
+	run_parallel_test_and_modify_ ## size(void *arg)		\
+	{								\
+		struct parallel_test_and_set_lcore_ ## size *lcore = arg; \
+		uint64_t deadline = rte_get_timer_cycles() +		\
+			PARALLEL_TEST_RUNTIME * rte_get_timer_hz();	\
+		do {							\
+			bool old_value;					\
+			bool new_value = rte_rand() & 1;		\
+			bool use_assign = rte_rand() & 1;		\
+									\
+			if (use_assign)					\
+				old_value = rte_bit_atomic_test_and_assign( \
+					lcore->word, lcore->bit, new_value, \
+					rte_memory_order_relaxed);	\
+			else						\
+				old_value = new_value ?			\
+					rte_bit_atomic_test_and_set(	\
+						lcore->word, lcore->bit, \
+						rte_memory_order_relaxed) : \
+					rte_bit_atomic_test_and_clear(	\
+						lcore->word, lcore->bit, \
+						rte_memory_order_relaxed); \
+			if (old_value != new_value)			\
+				lcore->flips++;				\
+		} while (rte_get_timer_cycles() < deadline);		\
+									\
+		return 0;						\
+	}								\
+									\
+	static int							\
+	test_bit_atomic_parallel_test_and_modify_ ## size(void)		\
+	{								\
+		unsigned int worker_lcore_id;				\
+		uint ## size ## _t word = 0;				\
+		unsigned int bit = rte_rand_max(size);			\
+		struct parallel_test_and_set_lcore_ ## size main = {	\
+			.word = &word,				       \
+			.bit = bit \
+		};							\
+		struct parallel_test_and_set_lcore_ ## size worker = {	\
+			.word = &word,					\
+			.bit = bit					\
+		};							\
+									\
+		if (rte_lcore_count() < 2) {				\
+			printf("Need multiple cores to run parallel test.\n"); \
+			return TEST_SKIPPED;				\
+		}							\
+									\
+		worker_lcore_id = rte_get_next_lcore(-1, 1, 0);		\
+									\
+		int rc = rte_eal_remote_launch(run_parallel_test_and_modify_ ## size, \
+					       &worker,	worker_lcore_id); \
+		TEST_ASSERT(rc == 0, "Worker thread launch failed");	\
+									\
+		run_parallel_test_and_modify_ ## size(&main);		\
+									\
+		rte_eal_mp_wait_lcore();				\
+									\
+		uint64_t total_flips = main.flips + worker.flips;	\
+		bool expected_value = total_flips % 2;			\
+									\
+		TEST_ASSERT(expected_value == rte_bit_test(&word, bit), \
+			    "After %"PRId64" flips, the bit value "	\
+			    "should be %d", total_flips, expected_value); \
+									\
+		uint64_t expected_word = 0;				\
+		rte_bit_assign(&expected_word, bit, expected_value);	\
+									\
+		TEST_ASSERT(expected_word == word, "Untouched bits have " \
+			    "changed value");				\
+									\
+		return TEST_SUCCESS;					\
+	}
+
+GEN_TEST_BIT_PARALLEL_TEST_AND_MODIFY(32)
+GEN_TEST_BIT_PARALLEL_TEST_AND_MODIFY(64)
+
 static uint32_t val32;
 static uint64_t val64;
 
@@ -178,6 +403,12 @@ static struct unit_test_suite test_suite = {
 		TEST_CASE(test_bit_access_64),
 		TEST_CASE(test_bit_once_access_32),
 		TEST_CASE(test_bit_once_access_64),
+		TEST_CASE(test_bit_atomic_access_32),
+		TEST_CASE(test_bit_atomic_access_64),
+		TEST_CASE(test_bit_atomic_parallel_assign_32),
+		TEST_CASE(test_bit_atomic_parallel_assign_64),
+		TEST_CASE(test_bit_atomic_parallel_test_and_modify_32),
+		TEST_CASE(test_bit_atomic_parallel_test_and_modify_64),
 		TEST_CASE(test_bit_relaxed_set),
 		TEST_CASE(test_bit_relaxed_clear),
 		TEST_CASE(test_bit_relaxed_test_set_clear),
diff --git a/lib/eal/include/rte_bitops.h b/lib/eal/include/rte_bitops.h
index 8c38a1ac03..bc6d79086b 100644
--- a/lib/eal/include/rte_bitops.h
+++ b/lib/eal/include/rte_bitops.h
@@ -485,7 +485,6 @@ extern "C" {
 		 uint32_t *: __rte_bit_atomic_test_and_clear32,		\
 		 uint64_t *: __rte_bit_atomic_test_and_clear64)(addr, nr, \
 								memory_order)
-
 /**
  * @warning
  * @b EXPERIMENTAL: this API may change without prior notice.
-- 
2.34.1