| Message ID | 3ab4c68503a3e3e1b4f11a0c0900b872cfc806f6.1621426820.git.dcaratti@redhat.com |
|---|---|
| State | New |
| Headers | show |
| Series | [net-next] net/sched: cls_api: increase max_reclassify_loop | expand |
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 40fbea626dfd..75e3a288a7c8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1531,7 +1531,7 @@ static inline int __tcf_classify(struct sk_buff *skb, u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; + const int max_reclassify_loop = 16; const struct tcf_proto *first_tp; int limit = 0;
modern userspace applications, like OVN, can configure the TC datapath to "recirculate" packets several times. If more than 4 "recirculation" rules are configured, packets can be dropped by __tcf_classify(). Changing the maximum number of reclassifications (from 4 to 16) should be sufficient to prevent drops in most use cases, and guard against loops at the same time. Signed-off-by: Davide Caratti <dcaratti@redhat.com> --- net/sched/cls_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)