net/tc: introduce TC_ACT_REINSERT.

This is similar TC_ACT_REDIRECT, but with a slightly different
semantic:
- on ingress the mirred skbs are passed to the target device
network stack without any additional check not scrubbing.
- the rcu-protected stats provided via the tcf_result struct
  are updated on error conditions.

This new tcfa_action value is not exposed to the user-space
and can be used only internally by clsact.

v1 -> v2: do not touch TC_ACT_REDIRECT code path, introduce
 a new action type instead
v2 -> v3:
 - rename the new action value TC_ACT_REINJECT, update the
   helper accordingly
 - take care of uncloned reinjected packets in XDP generic
   hook
v3 -> v4:
 - renamed again the new action value (JiriP)
v4 -> v5:
 - fix build error with !NET_CLS_ACT (kbuild bot)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 36 insertions, 1 deletions

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 6d02f31abba8..22bfc3a13c25 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -7,6 +7,9 @@
 #include <net/sch_generic.h>
 #include <net/act_api.h>
 
+/* TC action not accessible from user space */
+#define TC_ACT_REINSERT		(TC_ACT_VALUE_MAX + 1)
+
 /* Basic packet classifier frontend definitions. */
 
 struct tcf_walker {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index bcae181c1857..a6d00093f35e 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -235,6 +235,12 @@ struct tcf_result {
 			u32		classid;
 		};
 		const struct tcf_proto *goto_tp;
+
+		/* used by the TC_ACT_REINSERT action */
+		struct {
+			bool		ingress;
+			struct gnet_stats_queue *qstats;
+		};
 	};
 };
 
@@ -569,6 +575,15 @@ static inline void skb_reset_tc(struct sk_buff *skb)
 #endif
 }
 
+static inline bool skb_is_tc_redirected(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	return skb->tc_redirected;
+#else
+	return false;
+#endif
+}
+
 static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_CLS_ACT
@@ -1108,4 +1123,17 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
 void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
 			  struct mini_Qdisc __rcu **p_miniq);
 
+static inline void skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
+{
+	struct gnet_stats_queue *stats = res->qstats;
+	int ret;
+
+	if (res->ingress)
+		ret = netif_receive_skb(skb);
+	else
+		ret = dev_queue_xmit(skb);
+	if (ret && stats)
+		qstats_overlimit_inc(res->qstats);
+}
+
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 89031b5fef9f..38b0c414d780 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4252,7 +4252,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	/* Reinjected packets coming from act_mirred or similar should
 	 * not get XDP generic processing.
 	 */
-	if (skb_cloned(skb))
+	if (skb_cloned(skb) || skb_is_tc_redirected(skb))
 		return XDP_PASS;
 
 	/* XDP packets must be linear and must have sufficient headroom
@@ -4602,6 +4602,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		__skb_push(skb, skb->mac_len);
 		skb_do_redirect(skb);
 		return NULL;
+	case TC_ACT_REINSERT:
+		/* this does not scrub the packet, and updates stats on error */
+		skb_tc_reinsert(skb, &cl_res);
+		return NULL;
 	default:
 		break;
 	}