[PATCH v3 21/27] drivers/event: replace rte_atomic32 in selftests

[Stephen Hemminger]

Last callers in these selftests of the rte_atomicNN_*() family,
which is being deprecated.

Convert total_events from rte_atomic32_t to RTE_ATOMIC(uint32_t)
for the stack-local instance and __rte_atomic uint32_t * for the
pointer in test_core_param. Switch reads and updates to
rte_atomic_*_explicit().

Reads in the busy-loop checks and progress logs use relaxed: the
counter is purely a "drained yet?" signal and no data is published
through it. The fetch_sub on the dequeue path uses release in
octeontx (preserving the publish-after-mbuf-free ordering already
implied by the seq_cst sub it replaces) and relaxed in dpaa2.

The stack-local atomic_total_events is initialized by direct
assignment instead of rte_atomic32_set(), since it is written
before any worker is launched.

Signed-off-by: Stephen Hemminger <stephen at networkplumber.org>
---
 drivers/event/dpaa2/dpaa2_eventdev_selftest.c | 26 +++++----
 drivers/event/octeontx/ssovf_evdev_selftest.c | 58 ++++++++++---------
 2 files changed, 46 insertions(+), 38 deletions(-)

diff --git a/drivers/event/dpaa2/dpaa2_eventdev_selftest.c b/drivers/event/dpaa2/dpaa2_eventdev_selftest.c
index 9d4938efe6..2c688bd194 100644
--- a/drivers/event/dpaa2/dpaa2_eventdev_selftest.c
+++ b/drivers/event/dpaa2/dpaa2_eventdev_selftest.c
@@ -2,7 +2,7 @@
  * Copyright 2018-2019 NXP
  */
 
-#include <rte_atomic.h>
+#include <rte_stdatomic.h>
 #include <rte_common.h>
 #include <rte_cycles.h>
 #include <rte_debug.h>
@@ -49,7 +49,7 @@ struct event_attr {
 };
 
 struct test_core_param {
-	rte_atomic32_t *total_events;
+	__rte_atomic uint32_t *total_events;
 	uint64_t dequeue_tmo_ticks;
 	uint8_t port;
 	uint8_t sched_type;
@@ -444,10 +444,10 @@ worker_multi_port_fn(void *arg)
 	struct rte_event ev;
 	uint16_t valid_event;
 	uint8_t port = param->port;
-	rte_atomic32_t *total_events = param->total_events;
+	__rte_atomic uint32_t *total_events = param->total_events;
 	int ret;
 
-	while (rte_atomic32_read(total_events) > 0) {
+	while (rte_atomic_load_explicit(total_events, rte_memory_order_relaxed) > 0) {
 		valid_event = rte_event_dequeue_burst(evdev, port, &ev, 1, 0);
 		if (!valid_event)
 			continue;
@@ -455,13 +455,15 @@ worker_multi_port_fn(void *arg)
 		ret = validate_event(&ev);
 		RTE_TEST_ASSERT_SUCCESS(ret, "Failed to validate event");
 		rte_pktmbuf_free(ev.mbuf);
-		rte_atomic32_sub(total_events, 1);
+
+		rte_atomic_fetch_sub_explicit(total_events, 1,
+					      rte_memory_order_relaxed);
 	}
 	return 0;
 }
 
 static int
-wait_workers_to_join(int lcore, const rte_atomic32_t *count)
+wait_workers_to_join(int lcore, const __rte_atomic uint32_t *count)
 {
 	uint64_t cycles, print_cycles;
 
@@ -472,15 +474,15 @@ wait_workers_to_join(int lcore, const rte_atomic32_t *count)
 		uint64_t new_cycles = rte_get_timer_cycles();
 
 		if (new_cycles - print_cycles > rte_get_timer_hz()) {
-			dpaa2_evdev_dbg("\r%s: events %d", __func__,
-				rte_atomic32_read(count));
+			dpaa2_evdev_dbg("\r%s: events %u", __func__,
+					rte_atomic_load_explicit(count, rte_memory_order_relaxed));
 			print_cycles = new_cycles;
 		}
 		if (new_cycles - cycles > rte_get_timer_hz() * 10) {
 			dpaa2_evdev_info(
-				"%s: No schedules for seconds, deadlock (%d)",
+				"%s: No schedules for seconds, deadlock (%u)",
 				__func__,
-				rte_atomic32_read(count));
+				rte_atomic_load_explicit(count, rte_memory_order_relaxed));
 			rte_event_dev_dump(evdev, stdout);
 			cycles = new_cycles;
 			return -1;
@@ -500,13 +502,13 @@ launch_workers_and_wait(int (*main_worker)(void *),
 	int w_lcore;
 	int ret;
 	struct test_core_param *param;
-	rte_atomic32_t atomic_total_events;
+	RTE_ATOMIC(uint32_t) atomic_total_events;
 	uint64_t dequeue_tmo_ticks;
 
 	if (!nb_workers)
 		return 0;
 
-	rte_atomic32_set(&atomic_total_events, total_events);
+	atomic_total_events = total_events;
 	RTE_BUILD_BUG_ON(NUM_PACKETS < MAX_EVENTS);
 
 	param = malloc(sizeof(struct test_core_param) * nb_workers);
diff --git a/drivers/event/octeontx/ssovf_evdev_selftest.c b/drivers/event/octeontx/ssovf_evdev_selftest.c
index b54ae126d2..500762af78 100644
--- a/drivers/event/octeontx/ssovf_evdev_selftest.c
+++ b/drivers/event/octeontx/ssovf_evdev_selftest.c
@@ -4,7 +4,7 @@
 
 #include <stdlib.h>
 
-#include <rte_atomic.h>
+#include <rte_stdatomic.h>
 #include <rte_common.h>
 #include <rte_cycles.h>
 #include <rte_debug.h>
@@ -84,7 +84,7 @@ seqn_list_check(int limit)
 }
 
 struct test_core_param {
-	rte_atomic32_t *total_events;
+	__rte_atomic uint32_t *total_events;
 	uint64_t dequeue_tmo_ticks;
 	uint8_t port;
 	uint8_t sched_type;
@@ -558,10 +558,10 @@ worker_multi_port_fn(void *arg)
 	struct rte_event ev;
 	uint16_t valid_event;
 	uint8_t port = param->port;
-	rte_atomic32_t *total_events = param->total_events;
+	__rte_atomic uint32_t *total_events = param->total_events;
 	int ret;
 
-	while (rte_atomic32_read(total_events) > 0) {
+	while (rte_atomic_load_explicit(total_events, rte_memory_order_relaxed) > 0) {
 		valid_event = rte_event_dequeue_burst(evdev, port, &ev, 1, 0);
 		if (!valid_event)
 			continue;
@@ -569,13 +569,14 @@ worker_multi_port_fn(void *arg)
 		ret = validate_event(&ev);
 		RTE_TEST_ASSERT_SUCCESS(ret, "Failed to validate event");
 		rte_pktmbuf_free(ev.mbuf);
-		rte_atomic32_sub(total_events, 1);
+
+		rte_atomic_fetch_sub_explicit(total_events, 1, rte_memory_order_release);
 	}
 	return 0;
 }
 
 static inline int
-wait_workers_to_join(int lcore, const rte_atomic32_t *count)
+wait_workers_to_join(int lcore, const __rte_atomic uint32_t *count)
 {
 	uint64_t cycles, print_cycles;
 	RTE_SET_USED(count);
@@ -585,15 +586,15 @@ wait_workers_to_join(int lcore, const rte_atomic32_t *count)
 		uint64_t new_cycles = rte_get_timer_cycles();
 
 		if (new_cycles - print_cycles > rte_get_timer_hz()) {
-			ssovf_log_dbg("\r%s: events %d", __func__,
-				rte_atomic32_read(count));
+			ssovf_log_dbg("\r%s: events %u", __func__,
+				      rte_atomic_load_explicit(count, rte_memory_order_relaxed));
 			print_cycles = new_cycles;
 		}
 		if (new_cycles - cycles > rte_get_timer_hz() * 10) {
 			ssovf_log_dbg(
 				"%s: No schedules for seconds, deadlock (%d)",
 				__func__,
-				rte_atomic32_read(count));
+				rte_atomic_load_explicit(count, rte_memory_order_relaxed));
 			rte_event_dev_dump(evdev, stdout);
 			cycles = new_cycles;
 			return -1;
@@ -613,13 +614,13 @@ launch_workers_and_wait(int (*main_worker)(void *),
 	int w_lcore;
 	int ret;
 	struct test_core_param *param;
-	rte_atomic32_t atomic_total_events;
+	RTE_ATOMIC(uint32_t) atomic_total_events;
 	uint64_t dequeue_tmo_ticks;
 
 	if (!nb_workers)
 		return 0;
 
-	rte_atomic32_set(&atomic_total_events, total_events);
+	atomic_total_events = total_events;
 	seqn_list_init();
 
 	param = malloc(sizeof(struct test_core_param) * nb_workers);
@@ -889,10 +890,10 @@ worker_flow_based_pipeline(void *arg)
 	uint16_t valid_event;
 	uint8_t port = param->port;
 	uint8_t new_sched_type = param->sched_type;
-	rte_atomic32_t *total_events = param->total_events;
+	__rte_atomic uint32_t *total_events = param->total_events;
 	uint64_t dequeue_tmo_ticks = param->dequeue_tmo_ticks;
 
-	while (rte_atomic32_read(total_events) > 0) {
+	while (rte_atomic_load_explicit(total_events, rte_memory_order_relaxed) > 0) {
 		valid_event = rte_event_dequeue_burst(evdev, port, &ev, 1,
 					dequeue_tmo_ticks);
 		if (!valid_event)
@@ -910,7 +911,8 @@ worker_flow_based_pipeline(void *arg)
 		} else if (ev.sub_event_type == 1) { /* Events from stage 1*/
 			if (seqn_list_update(*rte_event_pmd_selftest_seqn(ev.mbuf)) == 0) {
 				rte_pktmbuf_free(ev.mbuf);
-				rte_atomic32_sub(total_events, 1);
+				rte_atomic_fetch_sub_explicit(total_events, 1,
+							      rte_memory_order_release);
 			} else {
 				ssovf_log_dbg("Failed to update seqn_list");
 				return -1;
@@ -1044,10 +1046,10 @@ worker_group_based_pipeline(void *arg)
 	uint16_t valid_event;
 	uint8_t port = param->port;
 	uint8_t new_sched_type = param->sched_type;
-	rte_atomic32_t *total_events = param->total_events;
+	__rte_atomic uint32_t *total_events = param->total_events;
 	uint64_t dequeue_tmo_ticks = param->dequeue_tmo_ticks;
 
-	while (rte_atomic32_read(total_events) > 0) {
+	while (rte_atomic_load_explicit(total_events, rte_memory_order_relaxed) > 0) {
 		valid_event = rte_event_dequeue_burst(evdev, port, &ev, 1,
 					dequeue_tmo_ticks);
 		if (!valid_event)
@@ -1065,7 +1067,8 @@ worker_group_based_pipeline(void *arg)
 		} else if (ev.queue_id == 1) { /* Events from stage 1(group 1)*/
 			if (seqn_list_update(*rte_event_pmd_selftest_seqn(ev.mbuf)) == 0) {
 				rte_pktmbuf_free(ev.mbuf);
-				rte_atomic32_sub(total_events, 1);
+				rte_atomic_fetch_sub_explicit(total_events, 1,
+							      rte_memory_order_release);
 			} else {
 				ssovf_log_dbg("Failed to update seqn_list");
 				return -1;
@@ -1203,16 +1206,17 @@ worker_flow_based_pipeline_max_stages_rand_sched_type(void *arg)
 	struct rte_event ev;
 	uint16_t valid_event;
 	uint8_t port = param->port;
-	rte_atomic32_t *total_events = param->total_events;
+	__rte_atomic uint32_t *total_events = param->total_events;
 
-	while (rte_atomic32_read(total_events) > 0) {
+	while (rte_atomic_load_explicit(total_events, rte_memory_order_relaxed) > 0) {
 		valid_event = rte_event_dequeue_burst(evdev, port, &ev, 1, 0);
 		if (!valid_event)
 			continue;
 
 		if (ev.sub_event_type == 255) { /* last stage */
 			rte_pktmbuf_free(ev.mbuf);
-			rte_atomic32_sub(total_events, 1);
+			rte_atomic_fetch_sub_explicit(total_events, 1,
+							      rte_memory_order_release);
 		} else {
 			ev.event_type = RTE_EVENT_TYPE_CPU;
 			ev.sub_event_type++;
@@ -1278,16 +1282,17 @@ worker_queue_based_pipeline_max_stages_rand_sched_type(void *arg)
 			    RTE_EVENT_DEV_ATTR_QUEUE_COUNT,
 			    &queue_count), "Queue count get failed");
 	uint8_t nr_queues = queue_count;
-	rte_atomic32_t *total_events = param->total_events;
+	__rte_atomic uint32_t *total_events = param->total_events;
 
-	while (rte_atomic32_read(total_events) > 0) {
+	while (rte_atomic_load_explicit(total_events, rte_memory_order_relaxed) > 0) {
 		valid_event = rte_event_dequeue_burst(evdev, port, &ev, 1, 0);
 		if (!valid_event)
 			continue;
 
 		if (ev.queue_id == nr_queues - 1) { /* last stage */
 			rte_pktmbuf_free(ev.mbuf);
-			rte_atomic32_sub(total_events, 1);
+			rte_atomic_fetch_sub_explicit(total_events, 1,
+							      rte_memory_order_release);
 		} else {
 			ev.event_type = RTE_EVENT_TYPE_CPU;
 			ev.queue_id++;
@@ -1320,16 +1325,17 @@ worker_mixed_pipeline_max_stages_rand_sched_type(void *arg)
 			    RTE_EVENT_DEV_ATTR_QUEUE_COUNT,
 			    &queue_count), "Queue count get failed");
 	uint8_t nr_queues = queue_count;
-	rte_atomic32_t *total_events = param->total_events;
+	__rte_atomic uint32_t *total_events = param->total_events;
 
-	while (rte_atomic32_read(total_events) > 0) {
+	while (rte_atomic_load_explicit(total_events, rte_memory_order_relaxed) > 0) {
 		valid_event = rte_event_dequeue_burst(evdev, port, &ev, 1, 0);
 		if (!valid_event)
 			continue;
 
 		if (ev.queue_id == nr_queues - 1) { /* Last stage */
 			rte_pktmbuf_free(ev.mbuf);
-			rte_atomic32_sub(total_events, 1);
+			rte_atomic_fetch_sub_explicit(total_events, 1,
+						      rte_memory_order_release);
 		} else {
 			ev.event_type = RTE_EVENT_TYPE_CPU;
 			ev.queue_id++;
-- 
2.53.0