bpf: use bulk free on filtered packets

When rte_pktmbuf_free_bulk is faster because it does single
mempool operation rather than per-packet.

Signed-off-by: Stephen Hemminger <[email protected]>
Acked-by: Konstantin Ananyev <[email protected]>
Reviewed-by: Marat Khalili <[email protected]>

Author: shemminger

lib/bpf/bpf_pkt.c

@@ -177,8 +177,7 @@ apply_filter(struct rte_mbuf *mb[], const uint64_t rc[], uint32_t num,
 
 	if (drop != 0) {
 		/* free filtered out mbufs */
-		for (i = 0; i != k; i++)
-			rte_pktmbuf_free(dr[i]);
+		rte_pktmbuf_free_bulk(dr, k);
 	} else {
 		/* copy filtered out mbufs beyond good ones */
 		for (i = 0; i != k; i++)