[dpdk-dev] [PATCH v4 07/11] event/octeontx: add single producer timer arm variant

[Pavan Nikhilesh]

When application creates the timer adapter by passing
`RTE_EVENT_TIMER_ADAPTER_F_SP_PUT` flag, we can optimize the arm sequence
by removing the locking overhead.

Signed-off-by: Pavan Nikhilesh <pbhagavatula at caviumnetworks.com>
---
 drivers/event/octeontx/timvf_evdev.c  | 19 ++++++++---
 drivers/event/octeontx/timvf_evdev.h  |  5 +++
 drivers/event/octeontx/timvf_worker.c | 37 +++++++++++++++++++++
 drivers/event/octeontx/timvf_worker.h | 47 +++++++++++++++++++++++++++
 4 files changed, 103 insertions(+), 5 deletions(-)

diff --git a/drivers/event/octeontx/timvf_evdev.c b/drivers/event/octeontx/timvf_evdev.c
index 5ffb460a8..3b698b7c8 100644
--- a/drivers/event/octeontx/timvf_evdev.c
+++ b/drivers/event/octeontx/timvf_evdev.c
@@ -180,6 +180,7 @@ timvf_ring_create(struct rte_event_timer_adapter *adptr)
 	struct timvf_ring *timr;
 	struct timvf_info tinfo;
 	const char *mempool_ops;
+	unsigned int mp_flags = 0;
 
 	if (timvf_info(&tinfo) < 0)
 		return -ENODEV;
@@ -213,6 +214,11 @@ timvf_ring_create(struct rte_event_timer_adapter *adptr)
 
 	timr->nb_chunks = nb_timers / nb_chunk_slots;
 
+	if (rcfg->flags & RTE_EVENT_TIMER_ADAPTER_F_SP_PUT) {
+		mp_flags = MEMPOOL_F_SP_PUT | MEMPOOL_F_SC_GET;
+		timvf_log_info("Using single producer mode");
+	}
+
 	timr->bkt = rte_zmalloc("octeontx_timvf_bucket",
 			(timr->nb_bkts) * sizeof(struct tim_mem_bucket),
 			0);
@@ -222,7 +228,7 @@ timvf_ring_create(struct rte_event_timer_adapter *adptr)
 	snprintf(pool_name, 30, "timvf_chunk_pool%d", timr->tim_ring_id);
 	timr->chunk_pool = (void *)rte_mempool_create_empty(pool_name,
 			timr->nb_chunks, TIM_CHUNK_SIZE, 0, 0, rte_socket_id(),
-			0);
+			mp_flags);
 
 	if (!timr->chunk_pool) {
 		rte_free(timr->bkt);
@@ -306,17 +312,20 @@ timvf_timer_adapter_caps_get(const struct rte_eventdev *dev, uint64_t flags,
 		uint8_t enable_stats)
 {
 	RTE_SET_USED(dev);
-	RTE_SET_USED(flags);
 
 	if (enable_stats) {
 		timvf_ops.stats_get   = timvf_stats_get;
 		timvf_ops.stats_reset = timvf_stats_reset;
 	}
 
-	if (enable_stats)
-		timvf_ops.arm_burst = timvf_timer_arm_burst_mp_stats;
+	if (flags & RTE_EVENT_TIMER_ADAPTER_F_SP_PUT)
+		timvf_ops.arm_burst = enable_stats ?
+			timvf_timer_arm_burst_sp_stats :
+			timvf_timer_arm_burst_sp;
 	else
-		timvf_ops.arm_burst = timvf_timer_arm_burst_mp;
+		timvf_ops.arm_burst = enable_stats ?
+			timvf_timer_arm_burst_mp_stats :
+			timvf_timer_arm_burst_mp;
 
 	timvf_ops.cancel_burst = timvf_timer_cancel_burst;
 	*caps = RTE_EVENT_TIMER_ADAPTER_CAP_INTERNAL_PORT;
diff --git a/drivers/event/octeontx/timvf_evdev.h b/drivers/event/octeontx/timvf_evdev.h
index cae949c73..01ffac09a 100644
--- a/drivers/event/octeontx/timvf_evdev.h
+++ b/drivers/event/octeontx/timvf_evdev.h
@@ -197,6 +197,11 @@ int timvf_timer_adapter_caps_get(const struct rte_eventdev *dev, uint64_t flags,
 		uint8_t enable_stats);
 uint16_t timvf_timer_cancel_burst(const struct rte_event_timer_adapter *adptr,
 		struct rte_event_timer **tim, const uint16_t nb_timers);
+uint16_t timvf_timer_arm_burst_sp(const struct rte_event_timer_adapter *adptr,
+		struct rte_event_timer **tim, const uint16_t nb_timers);
+uint16_t timvf_timer_arm_burst_sp_stats(
+		const struct rte_event_timer_adapter *adptr,
+		struct rte_event_timer **tim, const uint16_t nb_timers);
 uint16_t timvf_timer_arm_burst_mp(const struct rte_event_timer_adapter *adptr,
 		struct rte_event_timer **tim, const uint16_t nb_timers);
 uint16_t timvf_timer_arm_burst_mp_stats(
diff --git a/drivers/event/octeontx/timvf_worker.c b/drivers/event/octeontx/timvf_worker.c
index 38b16d1ce..52b212c44 100644
--- a/drivers/event/octeontx/timvf_worker.c
+++ b/drivers/event/octeontx/timvf_worker.c
@@ -64,6 +64,43 @@ timvf_timer_cancel_burst(const struct rte_event_timer_adapter *adptr,
 	return index;
 }
 
+uint16_t
+timvf_timer_arm_burst_sp(const struct rte_event_timer_adapter *adptr,
+		struct rte_event_timer **tim, const uint16_t nb_timers)
+{
+	int ret;
+	uint16_t index;
+	struct tim_mem_entry entry;
+	struct timvf_ring *timr = adptr->data->adapter_priv;
+	for (index = 0; index < nb_timers; index++) {
+		if (timvf_timer_reg_checks(timr, tim[index]))
+			break;
+
+		timvf_format_event(tim[index], &entry);
+		ret = timvf_add_entry_sp(timr, tim[index]->timeout_ticks,
+				tim[index], &entry);
+		if (unlikely(ret)) {
+			rte_errno = -ret;
+			break;
+		}
+	}
+
+	return index;
+}
+
+uint16_t
+timvf_timer_arm_burst_sp_stats(const struct rte_event_timer_adapter *adptr,
+		struct rte_event_timer **tim, const uint16_t nb_timers)
+{
+	uint16_t ret;
+	struct timvf_ring *timr = adptr->data->adapter_priv;
+
+	ret = timvf_timer_arm_burst_sp(adptr, tim, nb_timers);
+	timr->tim_arm_cnt += ret;
+
+	return ret;
+}
+
 uint16_t
 timvf_timer_arm_burst_mp(const struct rte_event_timer_adapter *adptr,
 		struct rte_event_timer **tim, const uint16_t nb_timers)
diff --git a/drivers/event/octeontx/timvf_worker.h b/drivers/event/octeontx/timvf_worker.h
index c20d4d0cd..c3a669de9 100644
--- a/drivers/event/octeontx/timvf_worker.h
+++ b/drivers/event/octeontx/timvf_worker.h
@@ -224,6 +224,53 @@ timvf_get_target_bucket(struct timvf_ring * const timr, const uint32_t rel_bkt)
 	return &timr->bkt[tbkt_id];
 }
 
+/* Single producer functions. */
+static inline int
+timvf_add_entry_sp(struct timvf_ring * const timr, const uint32_t rel_bkt,
+		struct rte_event_timer * const tim,
+		const struct tim_mem_entry * const pent)
+{
+	int16_t rem;
+	uint64_t lock_sema;
+	struct tim_mem_bucket *bkt;
+	struct tim_mem_entry *chunk;
+
+
+	bkt = timvf_get_target_bucket(timr, rel_bkt);
+__retry:
+	/*Get Bucket sema*/
+	lock_sema = timr_bkt_fetch_sema(bkt);
+	/* Bucket related checks. */
+	if (unlikely(timr_bkt_get_hbt(lock_sema)))
+		goto __retry;
+
+	/* Insert the work. */
+	rem = timr_bkt_fetch_rem(lock_sema);
+
+	if (!rem) {
+		chunk = timr->refill_chunk(bkt, timr);
+		if (unlikely(chunk == NULL)) {
+			timr_bkt_set_rem(bkt, 0);
+			tim->impl_opaque[0] = tim->impl_opaque[1] = 0;
+			tim->state = RTE_EVENT_TIMER_ERROR;
+			return -ENOMEM;
+		}
+		bkt->current_chunk = (uintptr_t) chunk;
+		timr_bkt_set_rem(bkt, nb_chunk_slots - 1);
+	} else {
+		chunk = (struct tim_mem_entry *)(uintptr_t)bkt->current_chunk;
+		chunk += nb_chunk_slots - rem;
+	}
+	/* Copy work entry. */
+	*chunk = *pent;
+	timr_bkt_inc_nent(bkt);
+
+	tim->impl_opaque[0] = (uintptr_t)chunk;
+	tim->impl_opaque[1] = (uintptr_t)bkt;
+	tim->state = RTE_EVENT_TIMER_ARMED;
+	return 0;
+}
+
 /* Multi producer functions. */
 static inline int
 timvf_add_entry_mp(struct timvf_ring * const timr, const uint32_t rel_bkt,
-- 
2.17.0