flow_offload: add reoffload process to update hw_count

Add reoffload process to update hw_count when driver
is inserted or removed.

We will delete the action if it is with skip_sw flag and
not offloaded to any hardware in reoffload process.

When reoffloading actions, we still offload the actions
that are added independent of filters.

Signed-off-by: Baowen Zheng <baowen.zheng@corigine.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/act_api.h

@@ -7,6 +7,7 @@
 */
 
 #include <linux/refcount.h>
+#include <net/flow_offload.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
 #include <net/net_namespace.h>
@@ -254,6 +255,8 @@ void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets,
 int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
 
 int tcf_action_update_hw_stats(struct tc_action *action);
+int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb,
+			    void *cb_priv, bool add);
 int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
 			     struct tcf_chain **handle,
 			     struct netlink_ext_ack *newchain);
@@ -265,6 +268,14 @@ DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
 #endif
 
 int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
+
+#else /* !CONFIG_NET_CLS_ACT */
+
+static inline int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb,
+					  void *cb_priv, bool add) {
+	return 0;
+}
+
 #endif /* CONFIG_NET_CLS_ACT */
 
 static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,

net/core/flow_offload.c

@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <net/act_api.h>
 #include <net/flow_offload.h>
 #include <linux/rtnetlink.h>
 #include <linux/mutex.h>
@@ -417,6 +418,8 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
 	existing_qdiscs_register(cb, cb_priv);
 	mutex_unlock(&flow_indr_block_lock);
 
+	tcf_action_reoffload_cb(cb, cb_priv, true);
+
 	return 0;
 }
 EXPORT_SYMBOL(flow_indr_dev_register);
@@ -469,6 +472,7 @@ void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv,
 	__flow_block_indr_cleanup(release, cb_priv, &cleanup_list);
 	mutex_unlock(&flow_indr_block_lock);
 
+	tcf_action_reoffload_cb(cb, cb_priv, false);
 	flow_block_indr_notify(&cleanup_list);
 	kfree(indr_dev);
 }

net/sched/act_api.c

@@ -137,6 +137,19 @@ static void offload_action_hw_count_set(struct tc_action *act,
 	act->in_hw_count = hw_count;
 }
 
+static void offload_action_hw_count_inc(struct tc_action *act,
+					u32 hw_count)
+{
+	act->in_hw_count += hw_count;
+}
+
+static void offload_action_hw_count_dec(struct tc_action *act,
+					u32 hw_count)
+{
+	act->in_hw_count = act->in_hw_count > hw_count ?
+			   act->in_hw_count - hw_count : 0;
+}
+
 static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act)
 {
 	if (is_tcf_pedit(act))
@@ -183,9 +196,8 @@ static int offload_action_init(struct flow_offload_action *fl_action,
 	return -EOPNOTSUPP;
 }
 
-static int tcf_action_offload_cmd(struct flow_offload_action *fl_act,
+static int tcf_action_offload_cmd_ex(struct flow_offload_action *fl_act,
-				  u32 *hw_count,
+				     u32 *hw_count)
-				  struct netlink_ext_ack *extack)
 {
 	int err;
 
@@ -200,9 +212,37 @@ static int tcf_action_offload_cmd(struct flow_offload_action *fl_act,
 	return 0;
 }
 
-/* offload the tc action after it is inserted */
+static int tcf_action_offload_cmd_cb_ex(struct flow_offload_action *fl_act,
-static int tcf_action_offload_add(struct tc_action *action,
+					u32 *hw_count,
-				  struct netlink_ext_ack *extack)
+					flow_indr_block_bind_cb_t *cb,
+					void *cb_priv)
+{
+	int err;
+
+	err = cb(NULL, NULL, cb_priv, TC_SETUP_ACT, NULL, fl_act, NULL);
+	if (err < 0)
+		return err;
+
+	if (hw_count)
+		*hw_count = 1;
+
+	return 0;
+}
+
+static int tcf_action_offload_cmd(struct flow_offload_action *fl_act,
+				  u32 *hw_count,
+				  flow_indr_block_bind_cb_t *cb,
+				  void *cb_priv)
+{
+	return cb ? tcf_action_offload_cmd_cb_ex(fl_act, hw_count,
+						 cb, cb_priv) :
+		    tcf_action_offload_cmd_ex(fl_act, hw_count);
+}
+
+static int tcf_action_offload_add_ex(struct tc_action *action,
+				     struct netlink_ext_ack *extack,
+				     flow_indr_block_bind_cb_t *cb,
+				     void *cb_priv)
 {
 	bool skip_sw = tc_act_skip_sw(action->tcfa_flags);
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {
@@ -231,9 +271,10 @@ static int tcf_action_offload_add(struct tc_action *action,
 		goto fl_err;
 	}
 
-	err = tcf_action_offload_cmd(fl_action, &in_hw_count, extack);
+	err = tcf_action_offload_cmd(fl_action, &in_hw_count, cb, cb_priv);
 	if (!err)
-		offload_action_hw_count_set(action, in_hw_count);
+		cb ? offload_action_hw_count_inc(action, in_hw_count) :
+		     offload_action_hw_count_set(action, in_hw_count);
 
 	if (skip_sw && !tc_act_in_hw(action))
 		err = -EINVAL;
@@ -246,6 +287,13 @@ fl_err:
 	return err;
 }
 
+/* offload the tc action after it is inserted */
+static int tcf_action_offload_add(struct tc_action *action,
+				  struct netlink_ext_ack *extack)
+{
+	return tcf_action_offload_add_ex(action, extack, NULL, NULL);
+}
+
 int tcf_action_update_hw_stats(struct tc_action *action)
 {
 	struct flow_offload_action fl_act = {};
@@ -258,7 +306,7 @@ int tcf_action_update_hw_stats(struct tc_action *action)
 	if (err)
 		return err;
 
-	err = tcf_action_offload_cmd(&fl_act, NULL, NULL);
+	err = tcf_action_offload_cmd(&fl_act, NULL, NULL, NULL);
 	if (!err) {
 		preempt_disable();
 		tcf_action_stats_update(action, fl_act.stats.bytes,
@@ -277,7 +325,9 @@ int tcf_action_update_hw_stats(struct tc_action *action)
 }
 EXPORT_SYMBOL(tcf_action_update_hw_stats);
 
-static int tcf_action_offload_del(struct tc_action *action)
+static int tcf_action_offload_del_ex(struct tc_action *action,
+				     flow_indr_block_bind_cb_t *cb,
+				     void *cb_priv)
 {
 	struct flow_offload_action fl_act = {};
 	u32 in_hw_count = 0;
@@ -290,16 +340,25 @@ static int tcf_action_offload_del(struct tc_action *action)
 	if (err)
 		return err;
 
-	err = tcf_action_offload_cmd(&fl_act, &in_hw_count, NULL);
+	err = tcf_action_offload_cmd(&fl_act, &in_hw_count, cb, cb_priv);
-	if (err)
+	if (err < 0)
 		return err;
 
-	if (action->in_hw_count != in_hw_count)
+	if (!cb && action->in_hw_count != in_hw_count)
 		return -EINVAL;
 
+	/* do not need to update hw state when deleting action */
+	if (cb && in_hw_count)
+		offload_action_hw_count_dec(action, in_hw_count);
+
 	return 0;
 }
 
+static int tcf_action_offload_del(struct tc_action *action)
+{
+	return tcf_action_offload_del_ex(action, NULL, NULL);
+}
+
 static void tcf_action_cleanup(struct tc_action *p)
 {
 	tcf_action_offload_del(p);
@@ -794,6 +853,59 @@ EXPORT_SYMBOL(tcf_idrinfo_destroy);
 
 static LIST_HEAD(act_base);
 static DEFINE_RWLOCK(act_mod_lock);
+/* since act ops id is stored in pernet subsystem list,
+ * then there is no way to walk through only all the action
+ * subsystem, so we keep tc action pernet ops id for
+ * reoffload to walk through.
+ */
+static LIST_HEAD(act_pernet_id_list);
+static DEFINE_MUTEX(act_id_mutex);
+struct tc_act_pernet_id {
+	struct list_head list;
+	unsigned int id;
+};
+
+static int tcf_pernet_add_id_list(unsigned int id)
+{
+	struct tc_act_pernet_id *id_ptr;
+	int ret = 0;
+
+	mutex_lock(&act_id_mutex);
+	list_for_each_entry(id_ptr, &act_pernet_id_list, list) {
+		if (id_ptr->id == id) {
+			ret = -EEXIST;
+			goto err_out;
+		}
+	}
+
+	id_ptr = kzalloc(sizeof(*id_ptr), GFP_KERNEL);
+	if (!id_ptr) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
+	id_ptr->id = id;
+
+	list_add_tail(&id_ptr->list, &act_pernet_id_list);
+
+err_out:
+	mutex_unlock(&act_id_mutex);
+	return ret;
+}
+
+static void tcf_pernet_del_id_list(unsigned int id)
+{
+	struct tc_act_pernet_id *id_ptr;
+
+	mutex_lock(&act_id_mutex);
+	list_for_each_entry(id_ptr, &act_pernet_id_list, list) {
+		if (id_ptr->id == id) {
+			list_del(&id_ptr->list);
+			kfree(id_ptr);
+			break;
+		}
+	}
+	mutex_unlock(&act_id_mutex);
+}
 
 int tcf_register_action(struct tc_action_ops *act,
 			struct pernet_operations *ops)
@@ -812,18 +924,31 @@ int tcf_register_action(struct tc_action_ops *act,
 	if (ret)
 		return ret;
 
+	if (ops->id) {
+		ret = tcf_pernet_add_id_list(*ops->id);
+		if (ret)
+			goto err_id;
+	}
+
 	write_lock(&act_mod_lock);
 	list_for_each_entry(a, &act_base, head) {
 		if (act->id == a->id || (strcmp(act->kind, a->kind) == 0)) {
-			write_unlock(&act_mod_lock);
+			ret = -EEXIST;
-			unregister_pernet_subsys(ops);
+			goto err_out;
-			return -EEXIST;
 		}
 	}
 	list_add_tail(&act->head, &act_base);
 	write_unlock(&act_mod_lock);
 
 	return 0;
+
+err_out:
+	write_unlock(&act_mod_lock);
+	if (ops->id)
+		tcf_pernet_del_id_list(*ops->id);
+err_id:
+	unregister_pernet_subsys(ops);
+	return ret;
 }
 EXPORT_SYMBOL(tcf_register_action);
 
@@ -842,8 +967,11 @@ int tcf_unregister_action(struct tc_action_ops *act,
 		}
 	}
 	write_unlock(&act_mod_lock);
-	if (!err)
+	if (!err) {
 		unregister_pernet_subsys(ops);
+		if (ops->id)
+			tcf_pernet_del_id_list(*ops->id);
+	}
 	return err;
 }
 EXPORT_SYMBOL(tcf_unregister_action);
@@ -1595,6 +1723,96 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[])
 	return 0;
 }
 
+static int
+tcf_reoffload_del_notify(struct net *net, struct tc_action *action)
+{
+	size_t attr_size = tcf_action_fill_size(action);
+	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {
+		[0] = action,
+	};
+	const struct tc_action_ops *ops = action->ops;
+	struct sk_buff *skb;
+	int ret;
+
+	skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size,
+			GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1) <= 0) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	ret = tcf_idr_release_unsafe(action);
+	if (ret == ACT_P_DELETED) {
+		module_put(ops->owner);
+		ret = rtnetlink_send(skb, net, 0, RTNLGRP_TC, 0);
+	} else {
+		kfree_skb(skb);
+	}
+
+	return ret;
+}
+
+int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb,
+			    void *cb_priv, bool add)
+{
+	struct tc_act_pernet_id *id_ptr;
+	struct tcf_idrinfo *idrinfo;
+	struct tc_action_net *tn;
+	struct tc_action *p;
+	unsigned int act_id;
+	unsigned long tmp;
+	unsigned long id;
+	struct idr *idr;
+	struct net *net;
+	int ret;
+
+	if (!cb)
+		return -EINVAL;
+
+	down_read(&net_rwsem);
+	mutex_lock(&act_id_mutex);
+
+	for_each_net(net) {
+		list_for_each_entry(id_ptr, &act_pernet_id_list, list) {
+			act_id = id_ptr->id;
+			tn = net_generic(net, act_id);
+			if (!tn)
+				continue;
+			idrinfo = tn->idrinfo;
+			if (!idrinfo)
+				continue;
+
+			mutex_lock(&idrinfo->lock);
+			idr = &idrinfo->action_idr;
+			idr_for_each_entry_ul(idr, p, tmp, id) {
+				if (IS_ERR(p) || tc_act_bind(p->tcfa_flags))
+					continue;
+				if (add) {
+					tcf_action_offload_add_ex(p, NULL, cb,
+								  cb_priv);
+					continue;
+				}
+
+				/* cb unregister to update hw count */
+				ret = tcf_action_offload_del_ex(p, cb, cb_priv);
+				if (ret < 0)
+					continue;
+				if (tc_act_skip_sw(p->tcfa_flags) &&
+				    !tc_act_in_hw(p))
+					tcf_reoffload_del_notify(net, p);
+			}
+			mutex_unlock(&idrinfo->lock);
+		}
+	}
+	mutex_unlock(&act_id_mutex);
+	up_read(&net_rwsem);
+
+	return 0;
+}
+
 static int
 tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
 	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)