[PATCH v2 09/12] app/compress: use compiler atomic builtins for display sync

[Joyce Kong]

Convert rte_atomic_test_and_set usage to compiler atomic
CAS operation for display sync.

Signed-off-by: Joyce Kong <joyce.kong at arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang at arm.com>
---
 app/test-compress-perf/comp_perf_test_common.h    |  2 +-
 .../comp_perf_test_cyclecount.c                   | 15 +++++++--------
 .../comp_perf_test_throughput.c                   | 10 +++++++---
 app/test-compress-perf/comp_perf_test_verify.c    |  6 ++++--
 4 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/app/test-compress-perf/comp_perf_test_common.h b/app/test-compress-perf/comp_perf_test_common.h
index 72705c6a2b..d039e5a29a 100644
--- a/app/test-compress-perf/comp_perf_test_common.h
+++ b/app/test-compress-perf/comp_perf_test_common.h
@@ -14,7 +14,7 @@ struct cperf_mem_resources {
 	uint16_t qp_id;
 	uint8_t lcore_id;
 
-	rte_atomic16_t print_info_once;
+	uint16_t print_info_once;
 
 	uint32_t total_bufs;
 	uint8_t *compressed_data;
diff --git a/app/test-compress-perf/comp_perf_test_cyclecount.c b/app/test-compress-perf/comp_perf_test_cyclecount.c
index c875ddbdac..da55b02b74 100644
--- a/app/test-compress-perf/comp_perf_test_cyclecount.c
+++ b/app/test-compress-perf/comp_perf_test_cyclecount.c
@@ -466,7 +466,7 @@ cperf_cyclecount_test_runner(void *test_ctx)
 	struct cperf_cyclecount_ctx *ctx = test_ctx;
 	struct comp_test_data *test_data = ctx->ver.options;
 	uint32_t lcore = rte_lcore_id();
-	static rte_atomic16_t display_once = RTE_ATOMIC16_INIT(0);
+	static uint16_t display_once;
 	static rte_spinlock_t print_spinlock;
 	int i;
 
@@ -486,10 +486,12 @@ cperf_cyclecount_test_runner(void *test_ctx)
 
 	ctx->ver.mem.lcore_id = lcore;
 
+	uint16_t exp = 0;
 	/*
 	 * printing information about current compression thread
 	 */
-	if (rte_atomic16_test_and_set(&ctx->ver.mem.print_info_once))
+	if (__atomic_compare_exchange_n(&ctx->ver.mem.print_info_once, &exp,
+				1, 0, __ATOMIC_RELAXED,  __ATOMIC_RELAXED))
 		printf("    lcore: %u,"
 				" driver name: %s,"
 				" device name: %s,"
@@ -546,9 +548,10 @@ cperf_cyclecount_test_runner(void *test_ctx)
 			(ctx->ver.mem.total_bufs * test_data->num_iter);
 
 	/* R E P O R T processing */
-	if (rte_atomic16_test_and_set(&display_once)) {
+	rte_spinlock_lock(&print_spinlock);
 
-		rte_spinlock_lock(&print_spinlock);
+	if (display_once == 0) {
+		display_once = 1;
 
 		printf("\nLegend for the table\n"
 		"  - Retries section: number of retries for the following operations:\n"
@@ -576,12 +579,8 @@ cperf_cyclecount_test_runner(void *test_ctx)
 			"setup/op",
 			"[C-e]", "[C-d]",
 			"[D-e]", "[D-d]");
-
-		rte_spinlock_unlock(&print_spinlock);
 	}
 
-	rte_spinlock_lock(&print_spinlock);
-
 	printf("%12u"
 	       "%6u"
 	       "%12zu"
diff --git a/app/test-compress-perf/comp_perf_test_throughput.c b/app/test-compress-perf/comp_perf_test_throughput.c
index 13922b658c..d3dff070b0 100644
--- a/app/test-compress-perf/comp_perf_test_throughput.c
+++ b/app/test-compress-perf/comp_perf_test_throughput.c
@@ -329,15 +329,17 @@ cperf_throughput_test_runner(void *test_ctx)
 	struct cperf_benchmark_ctx *ctx = test_ctx;
 	struct comp_test_data *test_data = ctx->ver.options;
 	uint32_t lcore = rte_lcore_id();
-	static rte_atomic16_t display_once = RTE_ATOMIC16_INIT(0);
+	static uint16_t display_once;
 	int i, ret = EXIT_SUCCESS;
 
 	ctx->ver.mem.lcore_id = lcore;
 
+	uint16_t exp = 0;
 	/*
 	 * printing information about current compression thread
 	 */
-	if (rte_atomic16_test_and_set(&ctx->ver.mem.print_info_once))
+	if (__atomic_compare_exchange_n(&ctx->ver.mem.print_info_once, &exp,
+				1, 0, __ATOMIC_RELAXED, __ATOMIC_RELAXED))
 		printf("    lcore: %u,"
 				" driver name: %s,"
 				" device name: %s,"
@@ -391,7 +393,9 @@ cperf_throughput_test_runner(void *test_ctx)
 	ctx->decomp_gbps = rte_get_tsc_hz() / ctx->decomp_tsc_byte * 8 /
 			1000000000;
 
-	if (rte_atomic16_test_and_set(&display_once)) {
+	exp = 0;
+	if (__atomic_compare_exchange_n(&display_once, &exp, 1, 0,
+			__ATOMIC_RELAXED, __ATOMIC_RELAXED)) {
 		printf("\n%12s%6s%12s%17s%15s%16s\n",
 			"lcore id", "Level", "Comp size", "Comp ratio [%]",
 			"Comp [Gbps]", "Decomp [Gbps]");
diff --git a/app/test-compress-perf/comp_perf_test_verify.c b/app/test-compress-perf/comp_perf_test_verify.c
index 5e13257b79..f6e21368e8 100644
--- a/app/test-compress-perf/comp_perf_test_verify.c
+++ b/app/test-compress-perf/comp_perf_test_verify.c
@@ -388,7 +388,7 @@ cperf_verify_test_runner(void *test_ctx)
 	struct cperf_verify_ctx *ctx = test_ctx;
 	struct comp_test_data *test_data = ctx->options;
 	int ret = EXIT_SUCCESS;
-	static rte_atomic16_t display_once = RTE_ATOMIC16_INIT(0);
+	static uint16_t display_once;
 	uint32_t lcore = rte_lcore_id();
 
 	ctx->mem.lcore_id = lcore;
@@ -427,8 +427,10 @@ cperf_verify_test_runner(void *test_ctx)
 	ctx->ratio = (double) ctx->comp_data_sz /
 			test_data->input_data_sz * 100;
 
+	uint16_t exp = 0;
 	if (!ctx->silent) {
-		if (rte_atomic16_test_and_set(&display_once)) {
+		if (__atomic_compare_exchange_n(&display_once, &exp, 1, 0,
+				__ATOMIC_RELAXED, __ATOMIC_RELAXED)) {
 			printf("%12s%6s%12s%17s\n",
 			    "lcore id", "Level", "Comp size", "Comp ratio [%]");
 		}
-- 
2.25.1