Merge branch 'ct-offload' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

3 files changed, 99 insertions, 18 deletions

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e91448640a4f..2b5b4ebda842 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -22,6 +22,7 @@
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
 #include <linux/jhash.h>
+#include <linux/rculist.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -354,7 +355,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 	if (!chain)
 		return NULL;
-	list_add_tail(&chain->list, &block->chain_list);
+	list_add_tail_rcu(&chain->list, &block->chain_list);
 	mutex_init(&chain->filter_chain_lock);
 	chain->block = block;
 	chain->index = chain_index;
@@ -394,7 +395,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain)
 
 	ASSERT_BLOCK_LOCKED(block);
 
-	list_del(&chain->list);
+	list_del_rcu(&chain->list);
 	if (!chain->index)
 		block->chain0.chain = NULL;
 
@@ -453,6 +454,20 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
 	return NULL;
 }
 
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block,
+					      u32 chain_index)
+{
+	struct tcf_chain *chain;
+
+	list_for_each_entry_rcu(chain, &block->chain_list, list) {
+		if (chain->index == chain_index)
+			return chain;
+	}
+	return NULL;
+}
+#endif
+
 static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
 			   u32 seq, u16 flags, int event, bool unicast);
 
@@ -1559,12 +1574,15 @@ static int tcf_block_setup(struct tcf_block *block,
  * to this qdisc, (optionally) tests for protocol and asks
  * specific classifiers.
  */
-int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
-		 struct tcf_result *res, bool compat_mode)
+static inline int __tcf_classify(struct sk_buff *skb,
+				 const struct tcf_proto *tp,
+				 const struct tcf_proto *orig_tp,
+				 struct tcf_result *res,
+				 bool compat_mode,
+				 u32 *last_executed_chain)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 4;
-	const struct tcf_proto *orig_tp = tp;
 	const struct tcf_proto *first_tp;
 	int limit = 0;
 
@@ -1582,21 +1600,11 @@ reclassify:
 #ifdef CONFIG_NET_CLS_ACT
 		if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) {
 			first_tp = orig_tp;
+			*last_executed_chain = first_tp->chain->index;
 			goto reset;
 		} else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) {
 			first_tp = res->goto_tp;
-
-#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
-			{
-				struct tc_skb_ext *ext;
-
-				ext = skb_ext_add(skb, TC_SKB_EXT);
-				if (WARN_ON_ONCE(!ext))
-					return TC_ACT_SHOT;
-
-				ext->chain = err & TC_ACT_EXT_VAL_MASK;
-			}
-#endif
+			*last_executed_chain = err & TC_ACT_EXT_VAL_MASK;
 			goto reset;
 		}
 #endif
@@ -1619,8 +1627,64 @@ reset:
 	goto reclassify;
 #endif
 }
+
+int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+		 struct tcf_result *res, bool compat_mode)
+{
+	u32 last_executed_chain = 0;
+
+	return __tcf_classify(skb, tp, tp, res, compat_mode,
+			      &last_executed_chain);
+}
 EXPORT_SYMBOL(tcf_classify);
 
+int tcf_classify_ingress(struct sk_buff *skb,
+			 const struct tcf_block *ingress_block,
+			 const struct tcf_proto *tp,
+			 struct tcf_result *res, bool compat_mode)
+{
+#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	u32 last_executed_chain = 0;
+
+	return __tcf_classify(skb, tp, tp, res, compat_mode,
+			      &last_executed_chain);
+#else
+	u32 last_executed_chain = tp ? tp->chain->index : 0;
+	const struct tcf_proto *orig_tp = tp;
+	struct tc_skb_ext *ext;
+	int ret;
+
+	ext = skb_ext_find(skb, TC_SKB_EXT);
+
+	if (ext && ext->chain) {
+		struct tcf_chain *fchain;
+
+		fchain = tcf_chain_lookup_rcu(ingress_block, ext->chain);
+		if (!fchain)
+			return TC_ACT_SHOT;
+
+		/* Consume, so cloned/redirect skbs won't inherit ext */
+		skb_ext_del(skb, TC_SKB_EXT);
+
+		tp = rcu_dereference_bh(fchain->filter_chain);
+	}
+
+	ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode,
+			     &last_executed_chain);
+
+	/* If we missed on some chain */
+	if (ret == TC_ACT_UNSPEC && last_executed_chain) {
+		ext = skb_ext_add(skb, TC_SKB_EXT);
+		if (WARN_ON_ONCE(!ext))
+			return TC_ACT_SHOT;
+		ext->chain = last_executed_chain;
+	}
+
+	return ret;
+#endif
+}
+EXPORT_SYMBOL(tcf_classify_ingress);
+
 struct tcf_chain_info {
 	struct tcf_proto __rcu **pprev;
 	struct tcf_proto __rcu *next;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6c9595f1048a..2efd5b61acef 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1391,6 +1391,14 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
 }
 EXPORT_SYMBOL(mini_qdisc_pair_swap);
 
+void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
+				struct tcf_block *block)
+{
+	miniqp->miniq1.block = block;
+	miniqp->miniq2.block = block;
+}
+EXPORT_SYMBOL(mini_qdisc_pair_block_init);
+
 void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
 			  struct mini_Qdisc __rcu **p_miniq)
 {
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index bf56aa519797..84838128b9c5 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -78,6 +78,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	int err;
 
 	net_inc_ingress_queue();
 
@@ -87,7 +88,13 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 	q->block_info.chain_head_change = clsact_chain_head_change;
 	q->block_info.chain_head_change_priv = &q->miniqp;
 
-	return tcf_block_get_ext(&q->block, sch, &q->block_info, extack);
+	err = tcf_block_get_ext(&q->block, sch, &q->block_info, extack);
+	if (err)
+		return err;
+
+	mini_qdisc_pair_block_init(&q->miniqp, q->block);
+
+	return 0;
 }
 
 static void ingress_destroy(struct Qdisc *sch)
@@ -226,6 +233,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 	if (err)
 		return err;
 
+	mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block);
+
 	mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
 
 	q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS;