1 files changed, 668 insertions, 163 deletions

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 537d0a0ad4c4..99ac747b7906 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -1,9 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NET_PKT_CLS_H
 #define __NET_PKT_CLS_H
 
 #include <linux/pkt_cls.h>
+#include <linux/workqueue.h>
 #include <net/sch_generic.h>
 #include <net/act_api.h>
+#include <net/net_namespace.h>
+
+/* TC action not accessible from user space */
+#define TC_ACT_CONSUMED		(TC_ACT_VALUE_MAX + 1)
 
 /* Basic packet classifier frontend definitions. */
 
@@ -11,26 +17,119 @@ struct tcf_walker {
 	int	stop;
 	int	skip;
 	int	count;
-	int	(*fn)(struct tcf_proto *, unsigned long node, struct tcf_walker *);
+	bool	nonempty;
+	unsigned long cookie;
+	int	(*fn)(struct tcf_proto *, void *node, struct tcf_walker *);
 };
 
 int register_tcf_proto_ops(struct tcf_proto_ops *ops);
-int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
+void unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
+#define NET_CLS_ALIAS_PREFIX "net-cls-"
+#define MODULE_ALIAS_NET_CLS(kind)	MODULE_ALIAS(NET_CLS_ALIAS_PREFIX kind)
+
+struct tcf_block_ext_info {
+	enum flow_block_binder_type binder_type;
+	tcf_chain_head_change_t *chain_head_change;
+	void *chain_head_change_priv;
+	u32 block_index;
+};
+
+struct tcf_qevent {
+	struct tcf_block	*block;
+	struct tcf_block_ext_info info;
+	struct tcf_proto __rcu *filter_chain;
+};
+
+struct tcf_block_cb;
+bool tcf_queue_work(struct rcu_work *rwork, work_func_t func);
 
 #ifdef CONFIG_NET_CLS
-struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
-				bool create);
-void tcf_chain_put(struct tcf_chain *chain);
+struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block,
+				       u32 chain_index);
+void tcf_chain_put_by_act(struct tcf_chain *chain);
+struct tcf_chain *tcf_get_next_chain(struct tcf_block *block,
+				     struct tcf_chain *chain);
+struct tcf_proto *tcf_get_next_proto(struct tcf_chain *chain,
+				     struct tcf_proto *tp);
+void tcf_block_netif_keep_dst(struct tcf_block *block);
 int tcf_block_get(struct tcf_block **p_block,
-		  struct tcf_proto __rcu **p_filter_chain);
+		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		  struct netlink_ext_ack *extack);
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei,
+		      struct netlink_ext_ack *extack);
 void tcf_block_put(struct tcf_block *block);
-int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
-		 struct tcf_result *res, bool compat_mode);
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei);
+int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action,
+		     int police, struct tcf_proto *tp, u32 handle, bool used_action_miss);
+
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+	return block->index;
+}
+
+static inline bool tcf_block_non_null_shared(struct tcf_block *block)
+{
+	return block && block->index;
+}
+
+#ifdef CONFIG_NET_CLS_ACT
+DECLARE_STATIC_KEY_FALSE(tcf_sw_enabled_key);
+
+static inline bool tcf_block_bypass_sw(struct tcf_block *block)
+{
+	return block && !atomic_read(&block->useswcnt);
+}
+#endif
+
+static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
+{
+	WARN_ON(tcf_block_shared(block));
+	return block->q;
+}
+
+int tcf_classify(struct sk_buff *skb,
+		 const struct tcf_block *block,
+		 const struct tcf_proto *tp, struct tcf_result *res,
+		 bool compat_mode);
+
+static inline bool tc_cls_stats_dump(struct tcf_proto *tp,
+				     struct tcf_walker *arg,
+				     void *filter)
+{
+	if (arg->count >= arg->skip && arg->fn(tp, filter, arg) < 0) {
+		arg->stop = 1;
+		return false;
+	}
+
+	arg->count++;
+	return true;
+}
 
 #else
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+	return false;
+}
+
+static inline bool tcf_block_non_null_shared(struct tcf_block *block)
+{
+	return false;
+}
+
 static inline
 int tcf_block_get(struct tcf_block **p_block,
-		  struct tcf_proto __rcu **p_filter_chain)
+		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		  struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static inline
+int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei,
+		      struct netlink_ext_ack *extack)
 {
 	return 0;
 }
@@ -39,11 +138,25 @@ static inline void tcf_block_put(struct tcf_block *block)
 {
 }
 
-static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+static inline
+void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei)
+{
+}
+
+static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
+{
+	return NULL;
+}
+
+static inline int tcf_classify(struct sk_buff *skb,
+			       const struct tcf_block *block,
+			       const struct tcf_proto *tp,
 			       struct tcf_result *res, bool compat_mode)
 {
 	return TC_ACT_UNSPEC;
 }
+
 #endif
 
 static inline unsigned long
@@ -52,37 +165,61 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-static inline unsigned long
-cls_set_class(struct tcf_proto *tp, unsigned long *clp, 
-	unsigned long cl)
+static inline void
+__tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
 {
-	unsigned long old_cl;
-	
-	tcf_tree_lock(tp);
-	old_cl = __cls_set_class(clp, cl);
-	tcf_tree_unlock(tp);
- 
-	return old_cl;
+	unsigned long cl;
+
+	cl = q->ops->cl_ops->bind_tcf(q, base, r->classid);
+	cl = __cls_set_class(&r->class, cl);
+	if (cl)
+		q->ops->cl_ops->unbind_tcf(q, cl);
 }
 
 static inline void
 tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base)
 {
-	unsigned long cl;
+	struct Qdisc *q = tp->chain->block->q;
 
-	cl = tp->q->ops->cl_ops->bind_tcf(tp->q, base, r->classid);
-	cl = cls_set_class(tp, &r->class, cl);
-	if (cl)
-		tp->q->ops->cl_ops->unbind_tcf(tp->q, cl);
+	/* Check q as it is not set for shared blocks. In that case,
+	 * setting class is not supported.
+	 */
+	if (!q)
+		return;
+	sch_tree_lock(q);
+	__tcf_bind_filter(q, r, base);
+	sch_tree_unlock(q);
 }
 
 static inline void
-tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
+__tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r)
 {
 	unsigned long cl;
 
 	if ((cl = __cls_set_class(&r->class, 0)) != 0)
-		tp->q->ops->cl_ops->unbind_tcf(tp->q, cl);
+		q->ops->cl_ops->unbind_tcf(q, cl);
+}
+
+static inline void
+tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r)
+{
+	struct Qdisc *q = tp->chain->block->q;
+
+	if (!q)
+		return;
+	__tcf_unbind_filter(q, r);
+}
+
+static inline void tc_cls_bind_class(u32 classid, unsigned long cl,
+				     void *q, struct tcf_result *res,
+				     unsigned long base)
+{
+	if (res->classid == classid) {
+		if (cl)
+			__tcf_bind_filter(q, res, base);
+		else
+			__tcf_unbind_filter(q, res);
+	}
 }
 
 struct tcf_exts {
@@ -90,6 +227,9 @@ struct tcf_exts {
 	__u32	type; /* for backward compat(TCA_OLD_COMPAT) */
 	int nr_actions;
 	struct tc_action **actions;
+	struct net	*net;
+	netns_tracker	ns_tracker;
+	struct tcf_exts_miss_cookie_node *miss_cookie_node;
 #endif
 	/* Map to export classifier specific extension TLV types to the
 	 * generic extensions API. Unsupported extensions must be set to 0.
@@ -98,81 +238,95 @@ struct tcf_exts {
 	int police;
 };
 
-static inline int tcf_exts_init(struct tcf_exts *exts, int action, int police)
+static inline int tcf_exts_init(struct tcf_exts *exts, struct net *net,
+				int action, int police)
 {
-#ifdef CONFIG_NET_CLS_ACT
-	exts->type = 0;
-	exts->nr_actions = 0;
-	exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *),
-				GFP_KERNEL);
-	if (!exts->actions)
-		return -ENOMEM;
+#ifdef CONFIG_NET_CLS
+	return tcf_exts_init_ex(exts, net, action, police, NULL, 0, false);
+#else
+	return -EOPNOTSUPP;
 #endif
-	exts->action = action;
-	exts->police = police;
-	return 0;
 }
 
-/**
- * tcf_exts_is_predicative - check if a predicative extension is present
- * @exts: tc filter extensions handle
- *
- * Returns 1 if a predicative extension is present, i.e. an extension which
- * might cause further actions and thus overrule the regular tcf_result.
+/* Return false if the netns is being destroyed in cleanup_net(). Callers
+ * need to do cleanup synchronously in this case, otherwise may race with
+ * tc_action_net_exit(). Return true for other cases.
  */
-static inline int
-tcf_exts_is_predicative(struct tcf_exts *exts)
+static inline bool tcf_exts_get_net(struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	return exts->nr_actions;
+	exts->net = maybe_get_net(exts->net);
+	if (exts->net)
+		netns_tracker_alloc(exts->net, &exts->ns_tracker, GFP_KERNEL);
+	return exts->net != NULL;
 #else
-	return 0;
+	return true;
 #endif
 }
 
-/**
- * tcf_exts_is_available - check if at least one extension is present
- * @exts: tc filter extensions handle
- *
- * Returns 1 if at least one extension is present.
- */
-static inline int
-tcf_exts_is_available(struct tcf_exts *exts)
+static inline void tcf_exts_put_net(struct tcf_exts *exts)
 {
-	/* All non-predicative extensions must be added here. */
-	return tcf_exts_is_predicative(exts);
+#ifdef CONFIG_NET_CLS_ACT
+	if (exts->net)
+		put_net_track(exts->net, &exts->ns_tracker);
+#endif
 }
 
-static inline void tcf_exts_to_list(const struct tcf_exts *exts,
-				    struct list_head *actions)
-{
 #ifdef CONFIG_NET_CLS_ACT
-	int i;
+#define tcf_exts_for_each_action(i, a, exts) \
+	for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = (exts)->actions[i]); i++)
+#else
+#define tcf_exts_for_each_action(i, a, exts) \
+	for (; 0; (void)(i), (void)(a), (void)(exts))
+#endif
 
-	for (i = 0; i < exts->nr_actions; i++) {
-		struct tc_action *a = exts->actions[i];
+#define tcf_act_for_each_action(i, a, actions) \
+	for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++)
 
-		list_add_tail(&a->list, actions);
-	}
-#endif
+static inline bool tc_act_in_hw(struct tc_action *act)
+{
+	return !!act->in_hw_count;
 }
 
 static inline void
-tcf_exts_stats_update(const struct tcf_exts *exts,
-		      u64 bytes, u64 packets, u64 lastuse)
+tcf_exts_hw_stats_update(const struct tcf_exts *exts,
+			 struct flow_stats *stats,
+			 bool use_act_stats)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	int i;
 
-	preempt_disable();
-
 	for (i = 0; i < exts->nr_actions; i++) {
 		struct tc_action *a = exts->actions[i];
 
-		tcf_action_stats_update(a, bytes, packets, lastuse);
+		if (use_act_stats || tc_act_in_hw(a)) {
+			if (!tcf_action_update_hw_stats(a))
+				continue;
+		}
+
+		preempt_disable();
+		tcf_action_stats_update(a, stats->bytes, stats->pkts, stats->drops,
+					stats->lastused, true);
+		preempt_enable();
+
+		a->used_hw_stats = stats->used_hw_stats;
+		a->used_hw_stats_valid = stats->used_hw_stats_valid;
 	}
+#endif
+}
 
-	preempt_enable();
+/**
+ * tcf_exts_has_actions - check if at least one action is present
+ * @exts: tc filter extensions handle
+ *
+ * Returns: true if at least one action is present.
+ */
+static inline bool tcf_exts_has_actions(struct tcf_exts *exts)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	return exts->nr_actions;
+#else
+	return false;
 #endif
 }
 
@@ -182,48 +336,51 @@ tcf_exts_stats_update(const struct tcf_exts *exts,
  * @exts: tc filter extensions handle
  * @res: desired result
  *
- * Executes all configured extensions. Returns 0 on a normal execution,
+ * Executes all configured extensions. Returns TC_ACT_OK on a normal execution,
  * a negative number if the filter must be considered unmatched or
  * a positive action code (TC_ACT_*) which must be returned to the
  * underlying layer.
  */
 static inline int
 tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,
-	       struct tcf_result *res)
+	      struct tcf_result *res)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	if (exts->nr_actions)
-		return tcf_action_exec(skb, exts->actions, exts->nr_actions,
-				       res);
+	return tcf_action_exec(skb, exts->actions, exts->nr_actions, res);
 #endif
-	return 0;
+	return TC_ACT_OK;
 }
 
+static inline int
+tcf_exts_exec_ex(struct sk_buff *skb, struct tcf_exts *exts, int act_index,
+		 struct tcf_result *res)
+{
 #ifdef CONFIG_NET_CLS_ACT
-
-#define tc_no_actions(_exts)  ((_exts)->nr_actions == 0)
-#define tc_single_action(_exts) ((_exts)->nr_actions == 1)
-
-#else /* CONFIG_NET_CLS_ACT */
-
-#define tc_no_actions(_exts) true
-#define tc_single_action(_exts) false
-
-#endif /* CONFIG_NET_CLS_ACT */
+	return tcf_action_exec(skb, exts->actions + act_index,
+			       exts->nr_actions - act_index, res);
+#else
+	return TC_ACT_OK;
+#endif
+}
 
 int tcf_exts_validate(struct net *net, struct tcf_proto *tp,
 		      struct nlattr **tb, struct nlattr *rate_tlv,
-		      struct tcf_exts *exts, bool ovr);
+		      struct tcf_exts *exts, u32 flags,
+		      struct netlink_ext_ack *extack);
+int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
+			 struct nlattr *rate_tlv, struct tcf_exts *exts,
+			 u32 flags, u32 fl_flags, struct netlink_ext_ack *extack);
 void tcf_exts_destroy(struct tcf_exts *exts);
-void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
-		     struct tcf_exts *src);
+void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src);
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts);
+int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts);
 int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts);
-int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
-		     struct net_device **hw_dev);
 
 /**
  * struct tcf_pkt_info - packet information
+ *
+ * @ptr: start of the pkt data
+ * @nexthdr: offset of the next header
  */
 struct tcf_pkt_info {
 	unsigned char *		ptr;
@@ -242,6 +399,7 @@ struct tcf_ematch_ops;
  * @ops: the operations lookup table of the corresponding ematch module
  * @datalen: length of the ematch specific configuration data
  * @data: ematch specific data
+ * @net: the network namespace
  */
 struct tcf_ematch {
 	struct tcf_ematch_ops * ops;
@@ -333,27 +491,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *,
 			struct tcf_pkt_info *);
 
 /**
- * tcf_em_tree_change - replace ematch tree of a running classifier
- *
- * @tp: classifier kind handle
- * @dst: destination ematch tree variable
- * @src: source ematch tree (temporary tree from tcf_em_tree_validate)
- *
- * This functions replaces the ematch tree in @dst with the ematch
- * tree in @src. The classifier in charge of the ematch tree may be
- * running.
- */
-static inline void tcf_em_tree_change(struct tcf_proto *tp,
-				      struct tcf_ematch_tree *dst,
-				      struct tcf_ematch_tree *src)
-{
-	tcf_tree_lock(tp);
-	memcpy(dst, src, sizeof(*dst));
-	tcf_tree_unlock(tp);
-}
-
-/**
- * tcf_em_tree_match - evaulate an ematch tree
+ * tcf_em_tree_match - evaluate an ematch tree
  *
  * @skb: socket buffer of the packet in question
  * @tree: ematch tree to be used for evaluation
@@ -363,7 +501,7 @@ static inline void tcf_em_tree_change(struct tcf_proto *tp,
  * through all ematches respecting their logic relations returning
  * as soon as the result is obvious.
  *
- * Returns 1 if the ematch tree as-one matches, no ematches are configured
+ * Returns: 1 if the ematch tree as-one matches, no ematches are configured
  * or ematch is not enabled in the kernel, otherwise 0 is returned.
  */
 static inline int tcf_em_tree_match(struct sk_buff *skb,
@@ -386,7 +524,6 @@ struct tcf_ematch_tree {
 #define tcf_em_tree_validate(tp, tb, t) ((void)(t), 0)
 #define tcf_em_tree_destroy(t) do { (void)(t); } while(0)
 #define tcf_em_tree_dump(skb, t, tlv) (0)
-#define tcf_em_tree_change(tp, dst, src) do { } while(0)
 #define tcf_em_tree_match(skb, t, info) ((void)(info), 1)
 
 #endif /* CONFIG_NET_EMATCH */
@@ -395,10 +532,12 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer)
 {
 	switch (layer) {
 		case TCF_LAYER_LINK:
-			return skb->data;
+			return skb_mac_header(skb);
 		case TCF_LAYER_NETWORK:
 			return skb_network_header(skb);
 		case TCF_LAYER_TRANSPORT:
+			if (!skb_transport_header_was_set(skb))
+				break;
 			return skb_transport_header(skb);
 	}
 
@@ -413,20 +552,24 @@ static inline int tcf_valid_offset(const struct sk_buff *skb,
 		      (ptr <= (ptr + len)));
 }
 
-#ifdef CONFIG_NET_CLS_IND
-#include <net/net_namespace.h>
-
 static inline int
-tcf_change_indev(struct net *net, struct nlattr *indev_tlv)
+tcf_change_indev(struct net *net, struct nlattr *indev_tlv,
+		 struct netlink_ext_ack *extack)
 {
 	char indev[IFNAMSIZ];
 	struct net_device *dev;
 
-	if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) >= IFNAMSIZ)
+	if (nla_strscpy(indev, indev_tlv, IFNAMSIZ) < 0) {
+		NL_SET_ERR_MSG_ATTR(extack, indev_tlv,
+				    "Interface name too long");
 		return -EINVAL;
+	}
 	dev = __dev_get_by_name(net, indev);
-	if (!dev)
+	if (!dev) {
+		NL_SET_ERR_MSG_ATTR(extack, indev_tlv,
+				    "Network device not found");
 		return -ENODEV;
+	}
 	return dev->ifindex;
 }
 
@@ -439,10 +582,81 @@ tcf_match_indev(struct sk_buff *skb, int ifindex)
 		return false;
 	return ifindex == skb->skb_iif;
 }
-#endif /* CONFIG_NET_CLS_IND */
+
+int tc_setup_offload_action(struct flow_action *flow_action,
+			    const struct tcf_exts *exts,
+			    struct netlink_ext_ack *extack);
+void tc_cleanup_offload_action(struct flow_action *flow_action);
+int tc_setup_action(struct flow_action *flow_action,
+		    struct tc_action *actions[],
+		    u32 miss_cookie_base,
+		    struct netlink_ext_ack *extack);
+
+int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
+		     void *type_data, bool err_stop, bool rtnl_held);
+int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp,
+		    enum tc_setup_type type, void *type_data, bool err_stop,
+		    u32 *flags, unsigned int *in_hw_count, bool rtnl_held);
+int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp,
+			enum tc_setup_type type, void *type_data, bool err_stop,
+			u32 *old_flags, unsigned int *old_in_hw_count,
+			u32 *new_flags, unsigned int *new_in_hw_count,
+			bool rtnl_held);
+int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp,
+			enum tc_setup_type type, void *type_data, bool err_stop,
+			u32 *flags, unsigned int *in_hw_count, bool rtnl_held);
+int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp,
+			  bool add, flow_setup_cb_t *cb,
+			  enum tc_setup_type type, void *type_data,
+			  void *cb_priv, u32 *flags, unsigned int *in_hw_count);
+unsigned int tcf_exts_num_actions(struct tcf_exts *exts);
+
+#ifdef CONFIG_NET_CLS_ACT
+int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch,
+		    enum flow_block_binder_type binder_type,
+		    struct nlattr *block_index_attr,
+		    struct netlink_ext_ack *extack);
+void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch);
+int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr,
+			       struct netlink_ext_ack *extack);
+struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb,
+				  struct sk_buff **to_free, int *ret);
+int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe);
+#else
+static inline int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch,
+				  enum flow_block_binder_type binder_type,
+				  struct nlattr *block_index_attr,
+				  struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static inline void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch)
+{
+}
+
+static inline int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr,
+					     struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static inline struct sk_buff *
+tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb,
+		  struct sk_buff **to_free, int *ret)
+{
+	return skb;
+}
+
+static inline int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe)
+{
+	return 0;
+}
+#endif
 
 struct tc_cls_u32_knode {
 	struct tcf_exts *exts;
+	struct tcf_result *res;
 	struct tc_u32_sel *sel;
 	u32 handle;
 	u32 val;
@@ -467,6 +681,7 @@ enum tc_clsu32_command {
 };
 
 struct tc_cls_u32_offload {
+	struct flow_cls_common_offload common;
 	/* knode values */
 	enum tc_clsu32_command command;
 	union {
@@ -475,19 +690,33 @@ struct tc_cls_u32_offload {
 	};
 };
 
-static inline bool tc_can_offload(const struct net_device *dev,
-				  const struct tcf_proto *tp)
+static inline bool tc_can_offload(const struct net_device *dev)
 {
-	const struct Qdisc *sch = tp->q;
-	const struct Qdisc_class_ops *cops = sch->ops->cl_ops;
+	return dev->features & NETIF_F_HW_TC;
+}
+
+static inline bool tc_can_offload_extack(const struct net_device *dev,
+					 struct netlink_ext_ack *extack)
+{
+	bool can = tc_can_offload(dev);
 
-	if (!(dev->features & NETIF_F_HW_TC))
+	if (!can)
+		NL_SET_ERR_MSG(extack, "TC offload is disabled on net device");
+
+	return can;
+}
+
+static inline bool
+tc_cls_can_offload_and_chain0(const struct net_device *dev,
+			      struct flow_cls_common_offload *common)
+{
+	if (!tc_can_offload_extack(dev, common->extack))
 		return false;
-	if (!dev->netdev_ops->ndo_setup_tc)
+	if (common->chain_index) {
+		NL_SET_ERR_MSG(common->extack,
+			       "Driver supports only offload of chain 0");
 		return false;
-	if (cops && cops->tcf_cl_offload)
-		return cops->tcf_cl_offload(tp->classid);
-
+	}
 	return true;
 }
 
@@ -496,14 +725,6 @@ static inline bool tc_skip_hw(u32 flags)
 	return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false;
 }
 
-static inline bool tc_should_offload(const struct net_device *dev,
-				     const struct tcf_proto *tp, u32 flags)
-{
-	if (tc_skip_hw(flags))
-		return false;
-	return tc_can_offload(dev, tp);
-}
-
 static inline bool tc_skip_sw(u32 flags)
 {
 	return (flags & TCA_CLS_FLAGS_SKIP_SW) ? true : false;
@@ -512,9 +733,11 @@ static inline bool tc_skip_sw(u32 flags)
 /* SKIP_HW and SKIP_SW are mutually exclusive flags. */
 static inline bool tc_flags_valid(u32 flags)
 {
-	if (flags & ~(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW))
+	if (flags & ~(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW |
+		      TCA_CLS_FLAGS_VERBOSE))
 		return false;
 
+	flags &= TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW;
 	if (!(flags ^ (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW)))
 		return false;
 
@@ -526,55 +749,337 @@ static inline bool tc_in_hw(u32 flags)
 	return (flags & TCA_CLS_FLAGS_IN_HW) ? true : false;
 }
 
-enum tc_fl_command {
-	TC_CLSFLOWER_REPLACE,
-	TC_CLSFLOWER_DESTROY,
-	TC_CLSFLOWER_STATS,
-};
+static inline void
+tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common,
+			   const struct tcf_proto *tp, u32 flags,
+			   struct netlink_ext_ack *extack)
+{
+	cls_common->chain_index = tp->chain->index;
+	cls_common->protocol = tp->protocol;
+	cls_common->prio = tp->prio >> 16;
+	cls_common->skip_sw = tc_skip_sw(flags);
+	if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE)
+		cls_common->extack = extack;
+}
 
-struct tc_cls_flower_offload {
-	enum tc_fl_command command;
-	u32 prio;
-	unsigned long cookie;
-	struct flow_dissector *dissector;
-	struct fl_flow_key *mask;
-	struct fl_flow_key *key;
-	struct tcf_exts *exts;
-};
+static inline void tcf_proto_update_usesw(struct tcf_proto *tp, u32 flags)
+{
+	if (tp->usesw)
+		return;
+	if (tc_skip_sw(flags) && tc_in_hw(flags))
+		return;
+	tp->usesw = true;
+}
+
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb)
+{
+	struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT);
+
+	if (tc_skb_ext)
+		memset(tc_skb_ext, 0, sizeof(*tc_skb_ext));
+	return tc_skb_ext;
+}
+#endif
 
 enum tc_matchall_command {
 	TC_CLSMATCHALL_REPLACE,
 	TC_CLSMATCHALL_DESTROY,
+	TC_CLSMATCHALL_STATS,
 };
 
 struct tc_cls_matchall_offload {
+	struct flow_cls_common_offload common;
 	enum tc_matchall_command command;
-	struct tcf_exts *exts;
+	struct flow_rule *rule;
+	struct flow_stats stats;
+	bool use_act_stats;
 	unsigned long cookie;
 };
 
 enum tc_clsbpf_command {
-	TC_CLSBPF_ADD,
-	TC_CLSBPF_REPLACE,
-	TC_CLSBPF_DESTROY,
+	TC_CLSBPF_OFFLOAD,
 	TC_CLSBPF_STATS,
 };
 
 struct tc_cls_bpf_offload {
+	struct flow_cls_common_offload common;
 	enum tc_clsbpf_command command;
 	struct tcf_exts *exts;
 	struct bpf_prog *prog;
+	struct bpf_prog *oldprog;
 	const char *name;
 	bool exts_integrated;
-	u32 gen_flags;
 };
 
-
 /* This structure holds cookie structure that is passed from user
  * to the kernel for actions and classifiers
  */
 struct tc_cookie {
 	u8  *data;
 	u32 len;
+	struct rcu_head rcu;
+};
+
+struct tc_qopt_offload_stats {
+	struct gnet_stats_basic_sync *bstats;
+	struct gnet_stats_queue *qstats;
+};
+
+enum tc_mq_command {
+	TC_MQ_CREATE,
+	TC_MQ_DESTROY,
+	TC_MQ_STATS,
+	TC_MQ_GRAFT,
+};
+
+struct tc_mq_opt_offload_graft_params {
+	unsigned long queue;
+	u32 child_handle;
+};
+
+struct tc_mq_qopt_offload {
+	enum tc_mq_command command;
+	u32 handle;
+	union {
+		struct tc_qopt_offload_stats stats;
+		struct tc_mq_opt_offload_graft_params graft_params;
+	};
+};
+
+enum tc_htb_command {
+	/* Root */
+	TC_HTB_CREATE, /* Initialize HTB offload. */
+	TC_HTB_DESTROY, /* Destroy HTB offload. */
+
+	/* Classes */
+	/* Allocate qid and create leaf. */
+	TC_HTB_LEAF_ALLOC_QUEUE,
+	/* Convert leaf to inner, preserve and return qid, create new leaf. */
+	TC_HTB_LEAF_TO_INNER,
+	/* Delete leaf, while siblings remain. */
+	TC_HTB_LEAF_DEL,
+	/* Delete leaf, convert parent to leaf, preserving qid. */
+	TC_HTB_LEAF_DEL_LAST,
+	/* TC_HTB_LEAF_DEL_LAST, but delete driver data on hardware errors. */
+	TC_HTB_LEAF_DEL_LAST_FORCE,
+	/* Modify parameters of a node. */
+	TC_HTB_NODE_MODIFY,
+
+	/* Class qdisc */
+	TC_HTB_LEAF_QUERY_QUEUE, /* Query qid by classid. */
+};
+
+struct tc_htb_qopt_offload {
+	struct netlink_ext_ack *extack;
+	enum tc_htb_command command;
+	u32 parent_classid;
+	u16 classid;
+	u16 qid;
+	u32 quantum;
+	u64 rate;
+	u64 ceil;
+	u8 prio;
+};
+
+#define TC_HTB_CLASSID_ROOT U32_MAX
+
+enum tc_red_command {
+	TC_RED_REPLACE,
+	TC_RED_DESTROY,
+	TC_RED_STATS,
+	TC_RED_XSTATS,
+	TC_RED_GRAFT,
+};
+
+struct tc_red_qopt_offload_params {
+	u32 min;
+	u32 max;
+	u32 probability;
+	u32 limit;
+	bool is_ecn;
+	bool is_harddrop;
+	bool is_nodrop;
+	struct gnet_stats_queue *qstats;
 };
+
+struct tc_red_qopt_offload {
+	enum tc_red_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_red_qopt_offload_params set;
+		struct tc_qopt_offload_stats stats;
+		struct red_stats *xstats;
+		u32 child_handle;
+	};
+};
+
+enum tc_gred_command {
+	TC_GRED_REPLACE,
+	TC_GRED_DESTROY,
+	TC_GRED_STATS,
+};
+
+struct tc_gred_vq_qopt_offload_params {
+	bool present;
+	u32 limit;
+	u32 prio;
+	u32 min;
+	u32 max;
+	bool is_ecn;
+	bool is_harddrop;
+	u32 probability;
+	/* Only need backlog, see struct tc_prio_qopt_offload_params */
+	u32 *backlog;
+};
+
+struct tc_gred_qopt_offload_params {
+	bool grio_on;
+	bool wred_on;
+	unsigned int dp_cnt;
+	unsigned int dp_def;
+	struct gnet_stats_queue *qstats;
+	struct tc_gred_vq_qopt_offload_params tab[MAX_DPs];
+};
+
+struct tc_gred_qopt_offload_stats {
+	struct gnet_stats_basic_sync bstats[MAX_DPs];
+	struct gnet_stats_queue qstats[MAX_DPs];
+	struct red_stats *xstats[MAX_DPs];
+};
+
+struct tc_gred_qopt_offload {
+	enum tc_gred_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_gred_qopt_offload_params set;
+		struct tc_gred_qopt_offload_stats stats;
+	};
+};
+
+enum tc_prio_command {
+	TC_PRIO_REPLACE,
+	TC_PRIO_DESTROY,
+	TC_PRIO_STATS,
+	TC_PRIO_GRAFT,
+};
+
+struct tc_prio_qopt_offload_params {
+	int bands;
+	u8 priomap[TC_PRIO_MAX + 1];
+	/* At the point of un-offloading the Qdisc, the reported backlog and
+	 * qlen need to be reduced by the portion that is in HW.
+	 */
+	struct gnet_stats_queue *qstats;
+};
+
+struct tc_prio_qopt_offload_graft_params {
+	u8 band;
+	u32 child_handle;
+};
+
+struct tc_prio_qopt_offload {
+	enum tc_prio_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_prio_qopt_offload_params replace_params;
+		struct tc_qopt_offload_stats stats;
+		struct tc_prio_qopt_offload_graft_params graft_params;
+	};
+};
+
+enum tc_root_command {
+	TC_ROOT_GRAFT,
+};
+
+struct tc_root_qopt_offload {
+	enum tc_root_command command;
+	u32 handle;
+	bool ingress;
+};
+
+enum tc_ets_command {
+	TC_ETS_REPLACE,
+	TC_ETS_DESTROY,
+	TC_ETS_STATS,
+	TC_ETS_GRAFT,
+};
+
+struct tc_ets_qopt_offload_replace_params {
+	unsigned int bands;
+	u8 priomap[TC_PRIO_MAX + 1];
+	unsigned int quanta[TCQ_ETS_MAX_BANDS];	/* 0 for strict bands. */
+	unsigned int weights[TCQ_ETS_MAX_BANDS];
+	struct gnet_stats_queue *qstats;
+};
+
+struct tc_ets_qopt_offload_graft_params {
+	u8 band;
+	u32 child_handle;
+};
+
+struct tc_ets_qopt_offload {
+	enum tc_ets_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_ets_qopt_offload_replace_params replace_params;
+		struct tc_qopt_offload_stats stats;
+		struct tc_ets_qopt_offload_graft_params graft_params;
+	};
+};
+
+enum tc_tbf_command {
+	TC_TBF_REPLACE,
+	TC_TBF_DESTROY,
+	TC_TBF_STATS,
+	TC_TBF_GRAFT,
+};
+
+struct tc_tbf_qopt_offload_replace_params {
+	struct psched_ratecfg rate;
+	u32 max_size;
+	struct gnet_stats_queue *qstats;
+};
+
+struct tc_tbf_qopt_offload {
+	enum tc_tbf_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_tbf_qopt_offload_replace_params replace_params;
+		struct tc_qopt_offload_stats stats;
+		u32 child_handle;
+	};
+};
+
+enum tc_fifo_command {
+	TC_FIFO_REPLACE,
+	TC_FIFO_DESTROY,
+	TC_FIFO_STATS,
+};
+
+struct tc_fifo_qopt_offload {
+	enum tc_fifo_command command;
+	u32 handle;
+	u32 parent;
+	union {
+		struct tc_qopt_offload_stats stats;
+	};
+};
+
+#ifdef CONFIG_NET_CLS_ACT
+DECLARE_STATIC_KEY_FALSE(tc_skb_ext_tc);
+void tc_skb_ext_tc_enable(void);
+void tc_skb_ext_tc_disable(void);
+#define tc_skb_ext_tc_enabled() static_branch_unlikely(&tc_skb_ext_tc)
+#else /* CONFIG_NET_CLS_ACT */
+static inline void tc_skb_ext_tc_enable(void) { }
+static inline void tc_skb_ext_tc_disable(void) { }
+#define tc_skb_ext_tc_enabled() false
+#endif
+
 #endif