Running l3fwd in event mode with SW eventdev, service cores can start RX before
main thread is finished with PMD installation.
Reproducible with latest dpdk main branch.
To reproduce:
./dpdk-l3fwd --lcores=49,51 -n 6 -a ca:00.0 -s 0x8000000000000 \
--vdev event_sw0 -- \
-L -P -p 1  --mode eventdev --eventq-sched=ordered \
--rule_ipv4=test/l3fwd_lpm_v4_u1.cfg \
--rule_ipv6=test/l3fwd_lpm_v6_u1.cfg --no-numa 

At init stage user will most likely see the error message like that:
ETHDEV: lcore 51 called rx_pkt_burst for not ready port 0
0: ./dpdk.org/x84_64-default-linuxapp-gcc10-dbg/examples/dpdk-l3fwd
(rte_dump_stack+0x1f) [15de723]
1: ./dpdk.org/x84_64-default-linuxapp-gcc10-dbg/examples/dpdk-l3fwd
(400000+0x107e167) [147e167]
2: ./dpdk.org/x84_64-default-linuxapp-gcc10-dbg/examples/dpdk-l3fwd
(400000+0xf1e5c8) [131e5c8]
....

And then all depends how luck/unlucky you are.
If there are some actual packet in HW RX queue, then the app will most
likely to crash, otherwise it might survive.
As error message suggests, the problem is that services are started before
main thread finished with NIC setup and initialisation.
The suggested fix moves services startup after NIC setup phase.

diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c
index 3bf28aec0c..0cfcaf45a6 100644
--- a/examples/l3fwd/main.c
+++ b/examples/l3fwd/main.c
@@ -1577,7 +1577,6 @@ main(int argc, char **argv)
                        l3fwd_lkp.main_loop = evt_rsrc->ops.fib_event_loop;
                else
                        l3fwd_lkp.main_loop = evt_rsrc->ops.lpm_event_loop;
-               l3fwd_event_service_setup();
        } else
 #endif
                l3fwd_poll_resource_setup();
@@ -1609,6 +1608,12 @@ main(int argc, char **argv)
                }
        }

+#ifdef RTE_LIB_EVENTDEV
+       if (evt_rsrc->enabled) {
+               l3fwd_event_service_setup();
+       }
+#endif
+
        printf("\n");

        for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {