event/octeontx2: remove hot spots by prefetching data

Recent profiling revealed few hotspots in octeontx2 event device
driver add prefetch hints to reduce stalls.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>

drivers/event/octeontx2/otx2_worker.h

@@ -280,6 +280,7 @@ otx2_ssogws_event_tx(struct otx2_ssogws *ws, struct rte_event ev[],
 	struct rte_mbuf *m = ev[0].mbuf;
 	const struct otx2_eth_txq *txq = otx2_ssogws_xtract_meta(m);
 
+	rte_prefetch_non_temporal(txq);
 	/* Perform header writes before barrier for TSO */
 	otx2_nix_xmit_prepare_tso(m, flags);
 	otx2_ssogws_order(ws, !ev->sched_type);

drivers/event/octeontx2/otx2_worker_dual.c

@@ -148,6 +148,7 @@ otx2_ssogws_dual_deq_ ##name(void *port, struct rte_event *ev,		\
 	struct otx2_ssogws_dual *ws = port;				\
 	uint8_t gw;							\
 									\
+	rte_prefetch_non_temporal(ws);					\
 	RTE_SET_USED(timeout_ticks);					\
 	if (ws->swtag_req) {						\
 		otx2_ssogws_swtag_wait((struct otx2_ssogws *)		\