net/sched/cls_api.c

/*
 * net/sched/cls_api.c	Packet classifier API.
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 * Changes:
 *
 * Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>

/* The list of all installed classifier types */
static LIST_HEAD(tcf_proto_base);

/* Protects list of registered TC modules. It is pure SMP lock. */
static DEFINE_RWLOCK(cls_mod_lock);

/* Find classifier type by string name */

static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind)
{
	const struct tcf_proto_ops *t, *res = NULL;

	if (kind) {
		read_lock(&cls_mod_lock);
		list_for_each_entry(t, &tcf_proto_base, head) {
			if (strcmp(kind, t->kind) == 0) {
				if (try_module_get(t->owner))
					res = t;
				break;
			}
		}
		read_unlock(&cls_mod_lock);
	}
	return res;
}

static const struct tcf_proto_ops *
tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack)
{
	const struct tcf_proto_ops *ops;

	ops = __tcf_proto_lookup_ops(kind);
	if (ops)
		return ops;
#ifdef CONFIG_MODULES
	rtnl_unlock();
	request_module("cls_%s", kind);
	rtnl_lock();
	ops = __tcf_proto_lookup_ops(kind);
	/* We dropped the RTNL semaphore in order to perform
	 * the module load. So, even if we succeeded in loading
	 * the module we have to replay the request. We indicate
	 * this using -EAGAIN.
	 */
	if (ops) {
		module_put(ops->owner);
		return ERR_PTR(-EAGAIN);
	}
#endif
	NL_SET_ERR_MSG(extack, "TC classifier not found");
	return ERR_PTR(-ENOENT);
}

/* Register(unregister) new classifier type */

int register_tcf_proto_ops(struct tcf_proto_ops *ops)
{
	struct tcf_proto_ops *t;
	int rc = -EEXIST;

	write_lock(&cls_mod_lock);
	list_for_each_entry(t, &tcf_proto_base, head)
		if (!strcmp(ops->kind, t->kind))
			goto out;

	list_add_tail(&ops->head, &tcf_proto_base);
	rc = 0;
out:
	write_unlock(&cls_mod_lock);
	return rc;
}
EXPORT_SYMBOL(register_tcf_proto_ops);

static struct workqueue_struct *tc_filter_wq;

int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
{
	struct tcf_proto_ops *t;
	int rc = -ENOENT;

	/* Wait for outstanding call_rcu()s, if any, from a
	 * tcf_proto_ops's destroy() handler.
	 */
	rcu_barrier();
	flush_workqueue(tc_filter_wq);

	write_lock(&cls_mod_lock);
	list_for_each_entry(t, &tcf_proto_base, head) {
		if (t == ops) {
			list_del(&t->head);
			rc = 0;
			break;
		}
	}
	write_unlock(&cls_mod_lock);
	return rc;
}
EXPORT_SYMBOL(unregister_tcf_proto_ops);

bool tcf_queue_work(struct rcu_work *rwork, work_func_t func)
{
	INIT_RCU_WORK(rwork, func);
	return queue_rcu_work(tc_filter_wq, rwork);
}
EXPORT_SYMBOL(tcf_queue_work);

/* Select new prio value from the range, managed by kernel. */

static inline u32 tcf_auto_prio(struct tcf_proto *tp)
{
	u32 first = TC_H_MAKE(0xC0000000U, 0U);

	if (tp)
		first = tp->prio - 1;

	return TC_H_MAJ(first);
}

static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
					  u32 prio, struct tcf_chain *chain,
					  struct netlink_ext_ack *extack)
{
	struct tcf_proto *tp;
	int err;

	tp = kzalloc(sizeof(*tp), GFP_KERNEL);
	if (!tp)
		return ERR_PTR(-ENOBUFS);

	tp->ops = tcf_proto_lookup_ops(kind, extack);
	if (IS_ERR(tp->ops)) {
		err = PTR_ERR(tp->ops);
		goto errout;
	}
	tp->classify = tp->ops->classify;
	tp->protocol = protocol;
	tp->prio = prio;
	tp->chain = chain;

	err = tp->ops->init(tp);
	if (err) {
		module_put(tp->ops->owner);
		goto errout;
	}
	return tp;

errout:
	kfree(tp);
	return ERR_PTR(err);
}

static void tcf_proto_destroy(struct tcf_proto *tp,
			      struct netlink_ext_ack *extack)
{
	tp->ops->destroy(tp, extack);
	module_put(tp->ops->owner);
	kfree_rcu(tp, rcu);
}

struct tcf_filter_chain_list_item {
	struct list_head list;
	tcf_chain_head_change_t *chain_head_change;
	void *chain_head_change_priv;
};

static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
					  u32 chain_index)
{
	struct tcf_chain *chain;

	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
	if (!chain)
		return NULL;
	list_add_tail(&chain->list, &block->chain_list);
	chain->block = block;
	chain->index = chain_index;
	chain->refcnt = 1;
	if (!chain->index)
		block->chain0.chain = chain;
	return chain;
}

static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item,
				       struct tcf_proto *tp_head)
{
	if (item->chain_head_change)
		item->chain_head_change(tp_head, item->chain_head_change_priv);
}

static void tcf_chain0_head_change(struct tcf_chain *chain,
				   struct tcf_proto *tp_head)
{
	struct tcf_filter_chain_list_item *item;
	struct tcf_block *block = chain->block;

	if (chain->index)
		return;
	list_for_each_entry(item, &block->chain0.filter_chain_list, list)
		tcf_chain_head_change_item(item, tp_head);
}

static void tcf_chain_destroy(struct tcf_chain *chain)
{
	struct tcf_block *block = chain->block;

	list_del(&chain->list);
	if (!chain->index)
		block->chain0.chain = NULL;
	kfree(chain);
	if (list_empty(&block->chain_list) && block->refcnt == 0)
		kfree(block);
}

static void tcf_chain_hold(struct tcf_chain *chain)
{
	++chain->refcnt;
}

static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain)
{
	/* In case all the references are action references, this
	 * chain should not be shown to the user.
	 */
	return chain->refcnt == chain->action_refcnt;
}

static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
					  u32 chain_index)
{
	struct tcf_chain *chain;

	list_for_each_entry(chain, &block->chain_list, list) {
		if (chain->index == chain_index)
			return chain;
	}
	return NULL;
}

static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
			   u32 seq, u16 flags, int event, bool unicast);

static struct tcf_chain *__tcf_chain_get(struct tcf_block *block,
					 u32 chain_index, bool create,
					 bool by_act)
{
	struct tcf_chain *chain = tcf_chain_lookup(block, chain_index);

	if (chain) {
		tcf_chain_hold(chain);
	} else {
		if (!create)
			return NULL;
		chain = tcf_chain_create(block, chain_index);
		if (!chain)
			return NULL;
	}

	if (by_act)
		++chain->action_refcnt;

	/* Send notification only in case we got the first
	 * non-action reference. Until then, the chain acts only as
	 * a placeholder for actions pointing to it and user ought
	 * not know about them.
	 */
	if (chain->refcnt - chain->action_refcnt == 1 && !by_act)
		tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
				RTM_NEWCHAIN, false);

	return chain;
}

static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
				       bool create)
{
	return __tcf_chain_get(block, chain_index, create, false);
}

struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index)
{
	return __tcf_chain_get(block, chain_index, true, true);
}
EXPORT_SYMBOL(tcf_chain_get_by_act);

static void tc_chain_tmplt_del(struct tcf_chain *chain);

static void __tcf_chain_put(struct tcf_chain *chain, bool by_act)
{
	if (by_act)
		chain->action_refcnt--;
	chain->refcnt--;

	/* The last dropped non-action reference will trigger notification. */
	if (chain->refcnt - chain->action_refcnt == 0 && !by_act)
		tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false);

	if (chain->refcnt == 0) {
		tc_chain_tmplt_del(chain);
		tcf_chain_destroy(chain);
	}
}

static void tcf_chain_put(struct tcf_chain *chain)
{
	__tcf_chain_put(chain, false);
}

void tcf_chain_put_by_act(struct tcf_chain *chain)
{
	__tcf_chain_put(chain, true);
}
EXPORT_SYMBOL(tcf_chain_put_by_act);

static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
{
	if (chain->explicitly_created)
		tcf_chain_put(chain);
}

static void tcf_chain_flush(struct tcf_chain *chain)
{
	struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);

	tcf_chain0_head_change(chain, NULL);
	while (tp) {
		RCU_INIT_POINTER(chain->filter_chain, tp->next);
		tcf_proto_destroy(tp, NULL);
		tp = rtnl_dereference(chain->filter_chain);
		tcf_chain_put(chain);
	}
}

static bool tcf_block_offload_in_use(struct tcf_block *block)
{
	return block->offloadcnt;
}

static int tcf_block_offload_cmd(struct tcf_block *block,
				 struct net_device *dev,
				 struct tcf_block_ext_info *ei,
				 enum tc_block_command command,
				 struct netlink_ext_ack *extack)
{
	struct tc_block_offload bo = {};

	bo.command = command;
	bo.binder_type = ei->binder_type;
	bo.block = block;
	bo.extack = extack;
	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
}

static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
				  struct tcf_block_ext_info *ei,
				  struct netlink_ext_ack *extack)
{
	struct net_device *dev = q->dev_queue->dev;
	int err;

	if (!dev->netdev_ops->ndo_setup_tc)
		goto no_offload_dev_inc;

	/* If tc offload feature is disabled and the block we try to bind
	 * to already has some offloaded filters, forbid to bind.
	 */
	if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) {
		NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled");
		return -EOPNOTSUPP;
	}

	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack);
	if (err == -EOPNOTSUPP)
		goto no_offload_dev_inc;
	return err;

no_offload_dev_inc:
	if (tcf_block_offload_in_use(block))
		return -EOPNOTSUPP;
	block->nooffloaddevcnt++;
	return 0;
}

static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
				     struct tcf_block_ext_info *ei)
{
	struct net_device *dev = q->dev_queue->dev;
	int err;

	if (!dev->netdev_ops->ndo_setup_tc)
		goto no_offload_dev_dec;
	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL);
	if (err == -EOPNOTSUPP)
		goto no_offload_dev_dec;
	return;

no_offload_dev_dec:
	WARN_ON(block->nooffloaddevcnt-- == 0);
}

static int
tcf_chain0_head_change_cb_add(struct tcf_block *block,
			      struct tcf_block_ext_info *ei,
			      struct netlink_ext_ack *extack)
{
	struct tcf_chain *chain0 = block->chain0.chain;
	struct tcf_filter_chain_list_item *item;

	item = kmalloc(sizeof(*item), GFP_KERNEL);
	if (!item) {
		NL_SET_ERR_MSG(extack, "Memory allocation for head change callback item failed");
		return -ENOMEM;
	}
	item->chain_head_change = ei->chain_head_change;
	item->chain_head_change_priv = ei->chain_head_change_priv;
	if (chain0 && chain0->filter_chain)
		tcf_chain_head_change_item(item, chain0->filter_chain);
	list_add(&item->list, &block->chain0.filter_chain_list);
	return 0;
}

static void
tcf_chain0_head_change_cb_del(struct tcf_block *block,
			      struct tcf_block_ext_info *ei)
{
	struct tcf_chain *chain0 = block->chain0.chain;
	struct tcf_filter_chain_list_item *item;

	list_for_each_entry(item, &block->chain0.filter_chain_list, list) {
		if ((!ei->chain_head_change && !ei->chain_head_change_priv) ||
		    (item->chain_head_change == ei->chain_head_change &&
		     item->chain_head_change_priv == ei->chain_head_change_priv)) {
			if (chain0)
				tcf_chain_head_change_item(item, NULL);
			list_del(&item->list);
			kfree(item);
			return;
		}
	}
	WARN_ON(1);
}

struct tcf_net {
	struct idr idr;
};

static unsigned int tcf_net_id;

static int tcf_block_insert(struct tcf_block *block, struct net *net,
			    struct netlink_ext_ack *extack)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	return idr_alloc_u32(&tn->idr, block, &block->index, block->index,
			     GFP_KERNEL);
}

static void tcf_block_remove(struct tcf_block *block, struct net *net)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	idr_remove(&tn->idr, block->index);
}

static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
					  u32 block_index,
					  struct netlink_ext_ack *extack)
{
	struct tcf_block *block;

	block = kzalloc(sizeof(*block), GFP_KERNEL);
	if (!block) {
		NL_SET_ERR_MSG(extack, "Memory allocation for block failed");
		return ERR_PTR(-ENOMEM);
	}
	INIT_LIST_HEAD(&block->chain_list);
	INIT_LIST_HEAD(&block->cb_list);
	INIT_LIST_HEAD(&block->owner_list);
	INIT_LIST_HEAD(&block->chain0.filter_chain_list);

	block->refcnt = 1;
	block->net = net;
	block->index = block_index;

	/* Don't store q pointer for blocks which are shared */
	if (!tcf_block_shared(block))
		block->q = q;
	return block;
}

static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	return idr_find(&tn->idr, block_index);
}

/* Find tcf block.
 * Set q, parent, cl when appropriate.
 */

static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
					u32 *parent, unsigned long *cl,
					int ifindex, u32 block_index,
					struct netlink_ext_ack *extack)
{
	struct tcf_block *block;

	if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
		block = tcf_block_lookup(net, block_index);
		if (!block) {
			NL_SET_ERR_MSG(extack, "Block of given index was not found");
			return ERR_PTR(-EINVAL);
		}
	} else {
		const struct Qdisc_class_ops *cops;
		struct net_device *dev;

		/* Find link */
		dev = __dev_get_by_index(net, ifindex);
		if (!dev)
			return ERR_PTR(-ENODEV);

		/* Find qdisc */
		if (!*parent) {
			*q = dev->qdisc;
			*parent = (*q)->handle;
		} else {
			*q = qdisc_lookup(dev, TC_H_MAJ(*parent));
			if (!*q) {
				NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
				return ERR_PTR(-EINVAL);
			}
		}

		/* Is it classful? */
		cops = (*q)->ops->cl_ops;
		if (!cops) {
			NL_SET_ERR_MSG(extack, "Qdisc not classful");
			return ERR_PTR(-EINVAL);
		}

		if (!cops->tcf_block) {
			NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
			return ERR_PTR(-EOPNOTSUPP);
		}

		/* Do we search for filter, attached to class? */
		if (TC_H_MIN(*parent)) {
			*cl = cops->find(*q, *parent);
			if (*cl == 0) {
				NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
				return ERR_PTR(-ENOENT);
			}
		}

		/* And the last stroke */
		block = cops->tcf_block(*q, *cl, extack);
		if (!block)
			return ERR_PTR(-EINVAL);
		if (tcf_block_shared(block)) {
			NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
			return ERR_PTR(-EOPNOTSUPP);
		}
	}

	return block;
}

struct tcf_block_owner_item {
	struct list_head list;
	struct Qdisc *q;
	enum tcf_block_binder_type binder_type;
};

static void
tcf_block_owner_netif_keep_dst(struct tcf_block *block,
			       struct Qdisc *q,
			       enum tcf_block_binder_type binder_type)
{
	if (block->keep_dst &&
	    binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
	    binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
		netif_keep_dst(qdisc_dev(q));
}

void tcf_block_netif_keep_dst(struct tcf_block *block)
{
	struct tcf_block_owner_item *item;

	block->keep_dst = true;
	list_for_each_entry(item, &block->owner_list, list)
		tcf_block_owner_netif_keep_dst(block, item->q,
					       item->binder_type);
}
EXPORT_SYMBOL(tcf_block_netif_keep_dst);

static int tcf_block_owner_add(struct tcf_block *block,
			       struct Qdisc *q,
			       enum tcf_block_binder_type binder_type)
{
	struct tcf_block_owner_item *item;

	item = kmalloc(sizeof(*item), GFP_KERNEL);
	if (!item)
		return -ENOMEM;
	item->q = q;
	item->binder_type = binder_type;
	list_add(&item->list, &block->owner_list);
	return 0;
}

static void tcf_block_owner_del(struct tcf_block *block,
				struct Qdisc *q,
				enum tcf_block_binder_type binder_type)
{
	struct tcf_block_owner_item *item;

	list_for_each_entry(item, &block->owner_list, list) {
		if (item->q == q && item->binder_type == binder_type) {
			list_del(&item->list);
			kfree(item);
			return;
		}
	}
	WARN_ON(1);
}

int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
		      struct tcf_block_ext_info *ei,
		      struct netlink_ext_ack *extack)
{
	struct net *net = qdisc_net(q);
	struct tcf_block *block = NULL;
	bool created = false;
	int err;

	if (ei->block_index) {
		/* block_index not 0 means the shared block is requested */
		block = tcf_block_lookup(net, ei->block_index);
		if (block)
			block->refcnt++;
	}

	if (!block) {
		block = tcf_block_create(net, q, ei->block_index, extack);
		if (IS_ERR(block))
			return PTR_ERR(block);
		created = true;
		if (tcf_block_shared(block)) {
			err = tcf_block_insert(block, net, extack);
			if (err)
				goto err_block_insert;
		}
	}

	err = tcf_block_owner_add(block, q, ei->binder_type);
	if (err)
		goto err_block_owner_add;

	tcf_block_owner_netif_keep_dst(block, q, ei->binder_type);

	err = tcf_chain0_head_change_cb_add(block, ei, extack);
	if (err)
		goto err_chain0_head_change_cb_add;

	err = tcf_block_offload_bind(block, q, ei, extack);
	if (err)
		goto err_block_offload_bind;

	*p_block = block;
	return 0;

err_block_offload_bind:
	tcf_chain0_head_change_cb_del(block, ei);
err_chain0_head_change_cb_add:
	tcf_block_owner_del(block, q, ei->binder_type);
err_block_owner_add:
	if (created) {
		if (tcf_block_shared(block))
			tcf_block_remove(block, net);
err_block_insert:
		kfree(block);
	} else {
		block->refcnt--;
	}
	return err;
}
EXPORT_SYMBOL(tcf_block_get_ext);

static void tcf_chain_head_change_dflt(struct tcf_proto *tp_head, void *priv)
{
	struct tcf_proto __rcu **p_filter_chain = priv;

	rcu_assign_pointer(*p_filter_chain, tp_head);
}

int tcf_block_get(struct tcf_block **p_block,
		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
		  struct netlink_ext_ack *extack)
{
	struct tcf_block_ext_info ei = {
		.chain_head_change = tcf_chain_head_change_dflt,
		.chain_head_change_priv = p_filter_chain,
	};

	WARN_ON(!p_filter_chain);
	return tcf_block_get_ext(p_block, q, &ei, extack);
}
EXPORT_SYMBOL(tcf_block_get);

/* XXX: Standalone actions are not allowed to jump to any chain, and bound
 * actions should be all removed after flushing.
 */
void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
		       struct tcf_block_ext_info *ei)
{
	struct tcf_chain *chain, *tmp;

	if (!block)
		return;
	tcf_chain0_head_change_cb_del(block, ei);
	tcf_block_owner_del(block, q, ei->binder_type);

	if (block->refcnt == 1) {
		if (tcf_block_shared(block))
			tcf_block_remove(block, block->net);

		/* Hold a refcnt for all chains, so that they don't disappear
		 * while we are iterating.
		 */
		list_for_each_entry(chain, &block->chain_list, list)
			tcf_chain_hold(chain);

		list_for_each_entry(chain, &block->chain_list, list)
			tcf_chain_flush(chain);
	}

	tcf_block_offload_unbind(block, q, ei);

	if (block->refcnt == 1) {
		/* At this point, all the chains should have refcnt >= 1. */
		list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
			tcf_chain_put_explicitly_created(chain);
			tcf_chain_put(chain);
		}

		block->refcnt--;
		if (list_empty(&block->chain_list))
			kfree(block);
	}
}
EXPORT_SYMBOL(tcf_block_put_ext);

void tcf_block_put(struct tcf_block *block)
{
	struct tcf_block_ext_info ei = {0, };

	if (!block)
		return;
	tcf_block_put_ext(block, block->q, &ei);
}

EXPORT_SYMBOL(tcf_block_put);

struct tcf_block_cb {
	struct list_head list;
	tc_setup_cb_t *cb;
	void *cb_ident;
	void *cb_priv;
	unsigned int refcnt;
};

void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
{
	return block_cb->cb_priv;
}
EXPORT_SYMBOL(tcf_block_cb_priv);

struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
					 tc_setup_cb_t *cb, void *cb_ident)
{	struct tcf_block_cb *block_cb;

	list_for_each_entry(block_cb, &block->cb_list, list)
		if (block_cb->cb == cb && block_cb->cb_ident == cb_ident)
			return block_cb;
	return NULL;
}
EXPORT_SYMBOL(tcf_block_cb_lookup);

void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
{
	block_cb->refcnt++;
}
EXPORT_SYMBOL(tcf_block_cb_incref);

unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
{
	return --block_cb->refcnt;
}
EXPORT_SYMBOL(tcf_block_cb_decref);

static int
tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
			    void *cb_priv, bool add, bool offload_in_use,
			    struct netlink_ext_ack *extack)
{
	struct tcf_chain *chain;
	struct tcf_proto *tp;
	int err;

	list_for_each_entry(chain, &block->chain_list, list) {
		for (tp = rtnl_dereference(chain->filter_chain); tp;
		     tp = rtnl_dereference(tp->next)) {
			if (tp->ops->reoffload) {
				err = tp->ops->reoffload(tp, add, cb, cb_priv,
							 extack);
				if (err && add)
					goto err_playback_remove;
			} else if (add && offload_in_use) {
				err = -EOPNOTSUPP;
				NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support");
				goto err_playback_remove;
			}
		}
	}

	return 0;

err_playback_remove:
	tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
				    extack);
	return err;
}

struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
					     tc_setup_cb_t *cb, void *cb_ident,
					     void *cb_priv,
					     struct netlink_ext_ack *extack)
{
	struct tcf_block_cb *block_cb;
	int err;

	/* Replay any already present rules */
	err = tcf_block_playback_offloads(block, cb, cb_priv, true,
					  tcf_block_offload_in_use(block),
					  extack);
	if (err)
		return ERR_PTR(err);

	block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
	if (!block_cb)
		return ERR_PTR(-ENOMEM);
	block_cb->cb = cb;
	block_cb->cb_ident = cb_ident;
	block_cb->cb_priv = cb_priv;
	list_add(&block_cb->list, &block->cb_list);
	return block_cb;
}
EXPORT_SYMBOL(__tcf_block_cb_register);

int tcf_block_cb_register(struct tcf_block *block,
			  tc_setup_cb_t *cb, void *cb_ident,
			  void *cb_priv, struct netlink_ext_ack *extack)
{
	struct tcf_block_cb *block_cb;

	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
					   extack);
	return PTR_ERR_OR_ZERO(block_cb);
}
EXPORT_SYMBOL(tcf_block_cb_register);

void __tcf_block_cb_unregister(struct tcf_block *block,
			       struct tcf_block_cb *block_cb)
{
	tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv,
				    false, tcf_block_offload_in_use(block),
				    NULL);
	list_del(&block_cb->list);
	kfree(block_cb);
}
EXPORT_SYMBOL(__tcf_block_cb_unregister);

void tcf_block_cb_unregister(struct tcf_block *block,
			     tc_setup_cb_t *cb, void *cb_ident)
{
	struct tcf_block_cb *block_cb;

	block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
	if (!block_cb)
		return;
	__tcf_block_cb_unregister(block, block_cb);
}
EXPORT_SYMBOL(tcf_block_cb_unregister);

static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
			     void *type_data, bool err_stop)
{
	struct tcf_block_cb *block_cb;
	int ok_count = 0;
	int err;

	/* Make sure all netdevs sharing this block are offload-capable. */
	if (block->nooffloaddevcnt && err_stop)
		return -EOPNOTSUPP;

	list_for_each_entry(block_cb, &block->cb_list, list) {
		err = block_cb->cb(type, type_data, block_cb->cb_priv);
		if (err) {
			if (err_stop)
				return err;
		} else {
			ok_count++;
		}
	}
	return ok_count;
}

/* Main classifier routine: scans classifier chain attached
 * 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)
{
	__be16 protocol = tc_skb_protocol(skb);
#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;

reclassify:
#endif
	for (; tp; tp = rcu_dereference_bh(tp->next)) {
		int err;

		if (tp->protocol != protocol &&
		    tp->protocol != htons(ETH_P_ALL))
			continue;

		err = tp->classify(skb, tp, res);
#ifdef CONFIG_NET_CLS_ACT
		if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) {
			first_tp = orig_tp;
			goto reset;
		} else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) {
			first_tp = res->goto_tp;
			goto reset;
		}
#endif
		if (err >= 0)
			return err;
	}

	return TC_ACT_UNSPEC; /* signal: continue lookup */
#ifdef CONFIG_NET_CLS_ACT
reset:
	if (unlikely(limit++ >= max_reclassify_loop)) {
		net_notice_ratelimited("%u: reclassify loop, rule prio %u, protocol %02x\n",
				       tp->chain->block->index,
				       tp->prio & 0xffff,
				       ntohs(tp->protocol));
		return TC_ACT_SHOT;
	}

	tp = first_tp;
	protocol = tc_skb_protocol(skb);
	goto reclassify;
#endif
}
EXPORT_SYMBOL(tcf_classify);

struct tcf_chain_info {
	struct tcf_proto __rcu **pprev;
	struct tcf_proto __rcu *next;
};

static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info)
{
	return rtnl_dereference(*chain_info->pprev);
}

static void tcf_chain_tp_insert(struct tcf_chain *chain,
				struct tcf_chain_info *chain_info,
				struct tcf_proto *tp)
{
	if (*chain_info->pprev == chain->filter_chain)
		tcf_chain0_head_change(chain, tp);
	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
	rcu_assign_pointer(*chain_info->pprev, tp);
	tcf_chain_hold(chain);
}

static void tcf_chain_tp_remove(struct tcf_chain *chain,
				struct tcf_chain_info *chain_info,
				struct tcf_proto *tp)
{
	struct tcf_proto *next = rtnl_dereference(chain_info->next);

	if (tp == chain->filter_chain)
		tcf_chain0_head_change(chain, next);
	RCU_INIT_POINTER(*chain_info->pprev, next);
	tcf_chain_put(chain);
}

static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
					   struct tcf_chain_info *chain_info,
					   u32 protocol, u32 prio,
					   bool prio_allocate)
{
	struct tcf_proto **pprev;
	struct tcf_proto *tp;

	/* Check the chain for existence of proto-tcf with this priority */
	for (pprev = &chain->filter_chain;
	     (tp = rtnl_dereference(*pprev)); pprev = &tp->next) {
		if (tp->prio >= prio) {
			if (tp->prio == prio) {
				if (prio_allocate ||
				    (tp->protocol != protocol && protocol))
					return ERR_PTR(-EINVAL);
			} else {
				tp = NULL;
			}
			break;
		}
	}
	chain_info->pprev = pprev;
	chain_info->next = tp ? tp->next : NULL;
	return tp;
}

static int tcf_fill_node(struct net *net, struct sk_buff *skb,
			 struct tcf_proto *tp, struct tcf_block *block,
			 struct Qdisc *q, u32 parent, void *fh,
			 u32 portid, u32 seq, u16 flags, int event)
{
	struct tcmsg *tcm;
	struct nlmsghdr  *nlh;
	unsigned char *b = skb_tail_pointer(skb);

	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
	if (!nlh)
		goto out_nlmsg_trim;
	tcm = nlmsg_data(nlh);
	tcm->tcm_family = AF_UNSPEC;
	tcm->tcm__pad1 = 0;
	tcm->tcm__pad2 = 0;
	if (q) {
		tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
		tcm->tcm_parent = parent;
	} else {
		tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
		tcm->tcm_block_index = block->index;
	}
	tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);
	if (nla_put_string(skb, TCA_KIND, tp->ops->kind))
		goto nla_put_failure;
	if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index))
		goto nla_put_failure;
	if (!fh) {
		tcm->tcm_handle = 0;
	} else {
		if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0)
			goto nla_put_failure;
	}
	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
	return skb->len;

out_nlmsg_trim:
nla_put_failure:
	nlmsg_trim(skb, b);
	return -1;
}

static int tfilter_notify(struct net *net, struct sk_buff *oskb,
			  struct nlmsghdr *n, struct tcf_proto *tp,
			  struct tcf_block *block, struct Qdisc *q,
			  u32 parent, void *fh, int event, bool unicast)
{
	struct sk_buff *skb;
	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (!skb)
		return -ENOBUFS;

	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
			  n->nlmsg_seq, n->nlmsg_flags, event) <= 0) {
		kfree_skb(skb);
		return -EINVAL;
	}

	if (unicast)
		return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);

	return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
			      n->nlmsg_flags & NLM_F_ECHO);
}

static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
			      struct nlmsghdr *n, struct tcf_proto *tp,
			      struct tcf_block *block, struct Qdisc *q,
			      u32 parent, void *fh, bool unicast, bool *last,
			      struct netlink_ext_ack *extack)
{
	struct sk_buff *skb;
	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
	int err;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (!skb)
		return -ENOBUFS;

	if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid,
			  n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) {
		NL_SET_ERR_MSG(extack, "Failed to build del event notification");
		kfree_skb(skb);
		return -EINVAL;
	}

	err = tp->ops->delete(tp, fh, last, extack);
	if (err) {
		kfree_skb(skb);
		return err;
	}

	if (unicast)
		return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);

	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
			     n->nlmsg_flags & NLM_F_ECHO);
	if (err < 0)
		NL_SET_ERR_MSG(extack, "Failed to send filter delete notification");
	return err;
}

static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
				 struct tcf_block *block, struct Qdisc *q,
				 u32 parent, struct nlmsghdr *n,
				 struct tcf_chain *chain, int event)
{
	struct tcf_proto *tp;

	for (tp = rtnl_dereference(chain->filter_chain);
	     tp; tp = rtnl_dereference(tp->next))
		tfilter_notify(net, oskb, n, tp, block,
			       q, parent, NULL, event, false);
}

static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct tcmsg *t;
	u32 protocol;
	u32 prio;
	bool prio_allocate;
	u32 parent;
	u32 chain_index;
	struct Qdisc *q = NULL;
	struct tcf_chain_info chain_info;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	struct tcf_proto *tp;
	unsigned long cl;
	void *fh;
	int err;
	int tp_created;

	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
		return -EPERM;

replay:
	tp_created = 0;

	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
	if (err < 0)
		return err;

	t = nlmsg_data(n);
	protocol = TC_H_MIN(t->tcm_info);
	prio = TC_H_MAJ(t->tcm_info);
	prio_allocate = false;
	parent = t->tcm_parent;
	cl = 0;

	if (prio == 0) {
		/* If no priority is provided by the user,
		 * we allocate one.
		 */
		if (n->nlmsg_flags & NLM_F_CREATE) {
			prio = TC_H_MAKE(0x80000000U, 0U);
			prio_allocate = true;
		} else {
			NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
			return -ENOENT;
		}
	}

	/* Find head of filter chain. */

	block = tcf_block_find(net, &q, &parent, &cl,
			       t->tcm_ifindex, t->tcm_block_index, extack);
	if (IS_ERR(block)) {
		err = PTR_ERR(block);
		goto errout;
	}

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
		err = -EINVAL;
		goto errout;
	}
	chain = tcf_chain_get(block, chain_index, true);
	if (!chain) {
		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
		err = -ENOMEM;
		goto errout;
	}

	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
			       prio, prio_allocate);
	if (IS_ERR(tp)) {
		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
		err = PTR_ERR(tp);
		goto errout;
	}

	if (tp == NULL) {
		/* Proto-tcf does not exist, create new one */

		if (tca[TCA_KIND] == NULL || !protocol) {
			NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified");
			err = -EINVAL;
			goto errout;
		}

		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
			NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
			err = -ENOENT;
			goto errout;
		}

		if (prio_allocate)
			prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info));

		tp = tcf_proto_create(nla_data(tca[TCA_KIND]),
				      protocol, prio, chain, extack);
		if (IS_ERR(tp)) {
			err = PTR_ERR(tp);
			goto errout;
		}
		tp_created = 1;
	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
		err = -EINVAL;
		goto errout;
	}

	fh = tp->ops->get(tp, t->tcm_handle);

	if (!fh) {
		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
			NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
			err = -ENOENT;
			goto errout;
		}
	} else if (n->nlmsg_flags & NLM_F_EXCL) {
		NL_SET_ERR_MSG(extack, "Filter already exists");
		err = -EEXIST;
		goto errout;
	}

	if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) {
		NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind");
		err = -EINVAL;
		goto errout;
	}

	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
			      n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE,
			      extack);
	if (err == 0) {
		if (tp_created)
			tcf_chain_tp_insert(chain, &chain_info, tp);
		tfilter_notify(net, skb, n, tp, block, q, parent, fh,
			       RTM_NEWTFILTER, false);
	} else {
		if (tp_created)
			tcf_proto_destroy(tp, NULL);
	}

errout:
	if (chain)
		tcf_chain_put(chain);
	if (err == -EAGAIN)
		/* Replay the request. */
		goto replay;
	return err;
}

static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct tcmsg *t;
	u32 protocol;
	u32 prio;
	u32 parent;
	u32 chain_index;
	struct Qdisc *q = NULL;
	struct tcf_chain_info chain_info;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	struct tcf_proto *tp = NULL;
	unsigned long cl = 0;
	void *fh = NULL;
	int err;

	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
		return -EPERM;

	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
	if (err < 0)
		return err;

	t = nlmsg_data(n);
	protocol = TC_H_MIN(t->tcm_info);
	prio = TC_H_MAJ(t->tcm_info);
	parent = t->tcm_parent;

	if (prio == 0 && (protocol || t->tcm_handle || tca[TCA_KIND])) {
		NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set");
		return -ENOENT;
	}

	/* Find head of filter chain. */

	block = tcf_block_find(net, &q, &parent, &cl,
			       t->tcm_ifindex, t->tcm_block_index, extack);
	if (IS_ERR(block)) {
		err = PTR_ERR(block);
		goto errout;
	}

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
		err = -EINVAL;
		goto errout;
	}
	chain = tcf_chain_get(block, chain_index, false);
	if (!chain) {
		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
		err = -EINVAL;
		goto errout;
	}

	if (prio == 0) {
		tfilter_notify_chain(net, skb, block, q, parent, n,
				     chain, RTM_DELTFILTER);
		tcf_chain_flush(chain);
		err = 0;
		goto errout;
	}

	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
			       prio, false);
	if (!tp || IS_ERR(tp)) {
		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
		err = tp ? PTR_ERR(tp) : -ENOENT;
		goto errout;
	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
		err = -EINVAL;
		goto errout;
	}

	fh = tp->ops->get(tp, t->tcm_handle);

	if (!fh) {
		if (t->tcm_handle == 0) {
			tcf_chain_tp_remove(chain, &chain_info, tp);
			tfilter_notify(net, skb, n, tp, block, q, parent, fh,
				       RTM_DELTFILTER, false);
			tcf_proto_destroy(tp, extack);
			err = 0;
		} else {
			NL_SET_ERR_MSG(extack, "Specified filter handle not found");
			err = -ENOENT;
		}
	} else {
		bool last;

		err = tfilter_del_notify(net, skb, n, tp, block,
					 q, parent, fh, false, &last,
					 extack);
		if (err)
			goto errout;
		if (last) {
			tcf_chain_tp_remove(chain, &chain_info, tp);
			tcf_proto_destroy(tp, extack);
		}
	}

errout:
	if (chain)
		tcf_chain_put(chain);
	return err;
}

static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
			  struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct tcmsg *t;
	u32 protocol;
	u32 prio;
	u32 parent;
	u32 chain_index;
	struct Qdisc *q = NULL;
	struct tcf_chain_info chain_info;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	struct tcf_proto *tp = NULL;
	unsigned long cl = 0;
	void *fh = NULL;
	int err;

	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
	if (err < 0)
		return err;

	t = nlmsg_data(n);
	protocol = TC_H_MIN(t->tcm_info);
	prio = TC_H_MAJ(t->tcm_info);
	parent = t->tcm_parent;

	if (prio == 0) {
		NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
		return -ENOENT;
	}

	/* Find head of filter chain. */

	block = tcf_block_find(net, &q, &parent, &cl,
			       t->tcm_ifindex, t->tcm_block_index, extack);
	if (IS_ERR(block)) {
		err = PTR_ERR(block);
		goto errout;
	}

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
		err = -EINVAL;
		goto errout;
	}
	chain = tcf_chain_get(block, chain_index, false);
	if (!chain) {
		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
		err = -EINVAL;
		goto errout;
	}

	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
			       prio, false);
	if (!tp || IS_ERR(tp)) {
		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
		err = tp ? PTR_ERR(tp) : -ENOENT;
		goto errout;
	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
		err = -EINVAL;
		goto errout;
	}

	fh = tp->ops->get(tp, t->tcm_handle);

	if (!fh) {
		NL_SET_ERR_MSG(extack, "Specified filter handle not found");
		err = -ENOENT;
	} else {
		err = tfilter_notify(net, skb, n, tp, block, q, parent,
				     fh, RTM_NEWTFILTER, true);
		if (err < 0)
			NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
	}

errout:
	if (chain)
		tcf_chain_put(chain);
	return err;
}

struct tcf_dump_args {
	struct tcf_walker w;
	struct sk_buff *skb;
	struct netlink_callback *cb;
	struct tcf_block *block;
	struct Qdisc *q;
	u32 parent;
};

static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg)
{
	struct tcf_dump_args *a = (void *)arg;
	struct net *net = sock_net(a->skb->sk);

	return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent,
			     n, NETLINK_CB(a->cb->skb).portid,
			     a->cb->nlh->nlmsg_seq, NLM_F_MULTI,
			     RTM_NEWTFILTER);
}

static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
			   struct sk_buff *skb, struct netlink_callback *cb,
			   long index_start, long *p_index)
{
	struct net *net = sock_net(skb->sk);
	struct tcf_block *block = chain->block;
	struct tcmsg *tcm = nlmsg_data(cb->nlh);
	struct tcf_dump_args arg;
	struct tcf_proto *tp;

	for (tp = rtnl_dereference(chain->filter_chain);
	     tp; tp = rtnl_dereference(tp->next), (*p_index)++) {
		if (*p_index < index_start)
			continue;
		if (TC_H_MAJ(tcm->tcm_info) &&
		    TC_H_MAJ(tcm->tcm_info) != tp->prio)
			continue;
		if (TC_H_MIN(tcm->tcm_info) &&
		    TC_H_MIN(tcm->tcm_info) != tp->protocol)
			continue;
		if (*p_index > index_start)
			memset(&cb->args[1], 0,
			       sizeof(cb->args) - sizeof(cb->args[0]));
		if (cb->args[1] == 0) {
			if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
					  NETLINK_CB(cb->skb).portid,
					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
					  RTM_NEWTFILTER) <= 0)
				return false;

			cb->args[1] = 1;
		}
		if (!tp->ops->walk)
			continue;
		arg.w.fn = tcf_node_dump;
		arg.skb = skb;
		arg.cb = cb;
		arg.block = block;
		arg.q = q;
		arg.parent = parent;
		arg.w.stop = 0;
		arg.w.skip = cb->args[1] - 1;
		arg.w.count = 0;
		arg.w.cookie = cb->args[2];
		tp->ops->walk(tp, &arg.w);
		cb->args[2] = arg.w.cookie;
		cb->args[1] = arg.w.count + 1;
		if (arg.w.stop)
			return false;
	}
	return true;
}

/* called with RTNL */
static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct Qdisc *q = NULL;
	struct tcf_block *block;
	struct tcf_chain *chain;
	struct tcmsg *tcm = nlmsg_data(cb->nlh);
	long index_start;
	long index;
	u32 parent;
	int err;

	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
		return skb->len;

	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
	if (err)
		return err;

	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
		block = tcf_block_lookup(net, tcm->tcm_block_index);
		if (!block)
			goto out;
		/* If we work with block index, q is NULL and parent value
		 * will never be used in the following code. The check
		 * in tcf_fill_node prevents it. However, compiler does not
		 * see that far, so set parent to zero to silence the warning
		 * about parent being uninitialized.
		 */
		parent = 0;
	} else {
		const struct Qdisc_class_ops *cops;
		struct net_device *dev;
		unsigned long cl = 0;

		dev = __dev_get_by_index(net, tcm->tcm_ifindex);
		if (!dev)
			return skb->len;

		parent = tcm->tcm_parent;
		if (!parent) {
			q = dev->qdisc;
			parent = q->handle;
		} else {
			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
		}
		if (!q)
			goto out;
		cops = q->ops->cl_ops;
		if (!cops)
			goto out;
		if (!cops->tcf_block)
			goto out;
		if (TC_H_MIN(tcm->tcm_parent)) {
			cl = cops->find(q, tcm->tcm_parent);
			if (cl == 0)
				goto out;
		}
		block = cops->tcf_block(q, cl, NULL);
		if (!block)
			goto out;
		if (tcf_block_shared(block))
			q = NULL;
	}

	index_start = cb->args[0];
	index = 0;

	list_for_each_entry(chain, &block->chain_list, list) {
		if (tca[TCA_CHAIN] &&
		    nla_get_u32(tca[TCA_CHAIN]) != chain->index)
			continue;
		if (!tcf_chain_dump(chain, q, parent, skb, cb,
				    index_start, &index)) {
			err = -EMSGSIZE;
			break;
		}
	}

	cb->args[0] = index;

out:
	/* If we did no progress, the error (EMSGSIZE) is real */
	if (skb->len == 0 && err)
		return err;
	return skb->len;
}

static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net,
			      struct sk_buff *skb, struct tcf_block *block,
			      u32 portid, u32 seq, u16 flags, int event)
{
	unsigned char *b = skb_tail_pointer(skb);
	const struct tcf_proto_ops *ops;
	struct nlmsghdr *nlh;
	struct tcmsg *tcm;
	void *priv;

	ops = chain->tmplt_ops;
	priv = chain->tmplt_priv;

	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
	if (!nlh)
		goto out_nlmsg_trim;
	tcm = nlmsg_data(nlh);
	tcm->tcm_family = AF_UNSPEC;
	tcm->tcm__pad1 = 0;
	tcm->tcm__pad2 = 0;
	tcm->tcm_handle = 0;
	if (block->q) {
		tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex;
		tcm->tcm_parent = block->q->handle;
	} else {
		tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
		tcm->tcm_block_index = block->index;
	}

	if (nla_put_u32(skb, TCA_CHAIN, chain->index))
		goto nla_put_failure;

	if (ops) {
		if (nla_put_string(skb, TCA_KIND, ops->kind))
			goto nla_put_failure;
		if (ops->tmplt_dump(skb, net, priv) < 0)
			goto nla_put_failure;
	}

	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
	return skb->len;

out_nlmsg_trim:
nla_put_failure:
	nlmsg_trim(skb, b);
	return -EMSGSIZE;
}

static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
			   u32 seq, u16 flags, int event, bool unicast)
{
	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
	struct tcf_block *block = chain->block;
	struct net *net = block->net;
	struct sk_buff *skb;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (!skb)
		return -ENOBUFS;

	if (tc_chain_fill_node(chain, net, skb, block, portid,
			       seq, flags, event) <= 0) {
		kfree_skb(skb);
		return -EINVAL;
	}

	if (unicast)
		return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);

	return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
}

static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
			      struct nlattr **tca,
			      struct netlink_ext_ack *extack)
{
	const struct tcf_proto_ops *ops;
	void *tmplt_priv;

	/* If kind is not set, user did not specify template. */
	if (!tca[TCA_KIND])
		return 0;

	ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack);
	if (IS_ERR(ops))
		return PTR_ERR(ops);
	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
		NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier");
		return -EOPNOTSUPP;
	}

	tmplt_priv = ops->tmplt_create(net, chain, tca, extack);
	if (IS_ERR(tmplt_priv)) {
		module_put(ops->owner);
		return PTR_ERR(tmplt_priv);
	}
	chain->tmplt_ops = ops;
	chain->tmplt_priv = tmplt_priv;
	return 0;
}

static void tc_chain_tmplt_del(struct tcf_chain *chain)
{
	const struct tcf_proto_ops *ops = chain->tmplt_ops;

	/* If template ops are set, no work to do for us. */
	if (!ops)
		return;

	ops->tmplt_destroy(chain->tmplt_priv);
	module_put(ops->owner);
}

/* Add/delete/get a chain */

static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
			struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct tcmsg *t;
	u32 parent;
	u32 chain_index;
	struct Qdisc *q = NULL;
	struct tcf_chain *chain = NULL;
	struct tcf_block *block;
	unsigned long cl;
	int err;

	if (n->nlmsg_type != RTM_GETCHAIN &&
	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
		return -EPERM;

replay:
	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
	if (err < 0)
		return err;

	t = nlmsg_data(n);
	parent = t->tcm_parent;
	cl = 0;

	block = tcf_block_find(net, &q, &parent, &cl,
			       t->tcm_ifindex, t->tcm_block_index, extack);
	if (IS_ERR(block))
		return PTR_ERR(block);

	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
	if (chain_index > TC_ACT_EXT_VAL_MASK) {
		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
		return -EINVAL;
	}
	chain = tcf_chain_lookup(block, chain_index);
	if (n->nlmsg_type == RTM_NEWCHAIN) {
		if (chain) {
			if (tcf_chain_held_by_acts_only(chain)) {
				/* The chain exists only because there is
				 * some action referencing it.
				 */
				tcf_chain_hold(chain);
			} else {
				NL_SET_ERR_MSG(extack, "Filter chain already exists");
				return -EEXIST;
			}
		} else {
			if (!(n->nlmsg_flags & NLM_F_CREATE)) {
				NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
				return -ENOENT;
			}
			chain = tcf_chain_create(block, chain_index);
			if (!chain) {
				NL_SET_ERR_MSG(extack, "Failed to create filter chain");
				return -ENOMEM;
			}
		}
	} else {
		if (!chain || tcf_chain_held_by_acts_only(chain)) {
			NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
			return -EINVAL;
		}
		tcf_chain_hold(chain);
	}

	switch (n->nlmsg_type) {
	case RTM_NEWCHAIN:
		err = tc_chain_tmplt_add(chain, net, tca, extack);
		if (err)
			goto errout;
		/* In case the chain was successfully added, take a reference
		 * to the chain. This ensures that an empty chain
		 * does not disappear at the end of this function.
		 */
		tcf_chain_hold(chain);
		chain->explicitly_created = true;
		tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
				RTM_NEWCHAIN, false);
		break;
	case RTM_DELCHAIN:
		/* Flush the chain first as the user requested chain removal. */
		tcf_chain_flush(chain);
		/* In case the chain was successfully deleted, put a reference
		 * to the chain previously taken during addition.
		 */
		tcf_chain_put_explicitly_created(chain);
		chain->explicitly_created = false;
		break;
	case RTM_GETCHAIN:
		err = tc_chain_notify(chain, skb, n->nlmsg_seq,
				      n->nlmsg_seq, n->nlmsg_type, true);
		if (err < 0)
			NL_SET_ERR_MSG(extack, "Failed to send chain notify message");
		break;
	default:
		err = -EOPNOTSUPP;
		NL_SET_ERR_MSG(extack, "Unsupported message type");
		goto errout;
	}

errout:
	tcf_chain_put(chain);
	if (err == -EAGAIN)
		/* Replay the request. */
		goto replay;
	return err;
}

/* called with RTNL */
static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tca[TCA_MAX + 1];
	struct Qdisc *q = NULL;
	struct tcf_block *block;
	struct tcf_chain *chain;
	struct tcmsg *tcm = nlmsg_data(cb->nlh);
	long index_start;
	long index;
	u32 parent;
	int err;

	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
		return skb->len;

	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
	if (err)
		return err;

	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
		block = tcf_block_lookup(net, tcm->tcm_block_index);
		if (!block)
			goto out;
		/* If we work with block index, q is NULL and parent value
		 * will never be used in the following code. The check
		 * in tcf_fill_node prevents it. However, compiler does not
		 * see that far, so set parent to zero to silence the warning
		 * about parent being uninitialized.
		 */
		parent = 0;
	} else {
		const struct Qdisc_class_ops *cops;
		struct net_device *dev;
		unsigned long cl = 0;

		dev = __dev_get_by_index(net, tcm->tcm_ifindex);
		if (!dev)
			return skb->len;

		parent = tcm->tcm_parent;
		if (!parent) {
			q = dev->qdisc;
			parent = q->handle;
		} else {
			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
		}
		if (!q)
			goto out;
		cops = q->ops->cl_ops;
		if (!cops)
			goto out;
		if (!cops->tcf_block)
			goto out;
		if (TC_H_MIN(tcm->tcm_parent)) {
			cl = cops->find(q, tcm->tcm_parent);
			if (cl == 0)
				goto out;
		}
		block = cops->tcf_block(q, cl, NULL);
		if (!block)
			goto out;
		if (tcf_block_shared(block))
			q = NULL;
	}

	index_start = cb->args[0];
	index = 0;

	list_for_each_entry(chain, &block->chain_list, list) {
		if ((tca[TCA_CHAIN] &&
		     nla_get_u32(tca[TCA_CHAIN]) != chain->index))
			continue;
		if (index < index_start) {
			index++;
			continue;
		}
		if (tcf_chain_held_by_acts_only(chain))
			continue;
		err = tc_chain_fill_node(chain, net, skb, block,
					 NETLINK_CB(cb->skb).portid,
					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
					 RTM_NEWCHAIN);
		if (err <= 0)
			break;
		index++;
	}

	cb->args[0] = index;

out:
	/* If we did no progress, the error (EMSGSIZE) is real */
	if (skb->len == 0 && err)
		return err;
	return skb->len;
}

void tcf_exts_destroy(struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
	tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
	kfree(exts->actions);
	exts->nr_actions = 0;
#endif
}
EXPORT_SYMBOL(tcf_exts_destroy);

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 netlink_ext_ack *extack)
{
#ifdef CONFIG_NET_CLS_ACT
	{
		struct tc_action *act;
		size_t attr_size = 0;

		if (exts->police && tb[exts->police]) {
			act = tcf_action_init_1(net, tp, tb[exts->police],
						rate_tlv, "police", ovr,
						TCA_ACT_BIND, true, extack);
			if (IS_ERR(act))
				return PTR_ERR(act);

			act->type = exts->type = TCA_OLD_COMPAT;
			exts->actions[0] = act;
			exts->nr_actions = 1;
		} else if (exts->action && tb[exts->action]) {
			int err;

			err = tcf_action_init(net, tp, tb[exts->action],
					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
					      exts->actions, &attr_size, true,
					      extack);
			if (err < 0)
				return err;
			exts->nr_actions = err;
		}
		exts->net = net;
	}
#else
	if ((exts->action && tb[exts->action]) ||
	    (exts->police && tb[exts->police])) {
		NL_SET_ERR_MSG(extack, "Classifier actions are not supported per compile options (CONFIG_NET_CLS_ACT)");
		return -EOPNOTSUPP;
	}
#endif

	return 0;
}
EXPORT_SYMBOL(tcf_exts_validate);

void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src)
{
#ifdef CONFIG_NET_CLS_ACT
	struct tcf_exts old = *dst;

	*dst = *src;
	tcf_exts_destroy(&old);
#endif
}
EXPORT_SYMBOL(tcf_exts_change);

#ifdef CONFIG_NET_CLS_ACT
static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts)
{
	if (exts->nr_actions == 0)
		return NULL;
	else
		return exts->actions[0];
}
#endif

int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
	struct nlattr *nest;

	if (exts->action && tcf_exts_has_actions(exts)) {
		/*
		 * again for backward compatible mode - we want
		 * to work with both old and new modes of entering
		 * tc data even if iproute2  was newer - jhs
		 */
		if (exts->type != TCA_OLD_COMPAT) {
			nest = nla_nest_start(skb, exts->action);
			if (nest == NULL)
				goto nla_put_failure;

			if (tcf_action_dump(skb, exts->actions, 0, 0) < 0)
				goto nla_put_failure;
			nla_nest_end(skb, nest);
		} else if (exts->police) {
			struct tc_action *act = tcf_exts_first_act(exts);
			nest = nla_nest_start(skb, exts->police);
			if (nest == NULL || !act)
				goto nla_put_failure;
			if (tcf_action_dump_old(skb, act, 0, 0) < 0)
				goto nla_put_failure;
			nla_nest_end(skb, nest);
		}
	}
	return 0;

nla_put_failure:
	nla_nest_cancel(skb, nest);
	return -1;
#else
	return 0;
#endif
}
EXPORT_SYMBOL(tcf_exts_dump);


int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
	struct tc_action *a = tcf_exts_first_act(exts);
	if (a != NULL && tcf_action_copy_stats(skb, a, 1) < 0)
		return -1;
#endif
	return 0;
}
EXPORT_SYMBOL(tcf_exts_dump_stats);

static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
				       enum tc_setup_type type,
				       void *type_data, bool err_stop)
{
	int ok_count = 0;
#ifdef CONFIG_NET_CLS_ACT
	const struct tc_action *a;
	struct net_device *dev;
	int i, ret;

	if (!tcf_exts_has_actions(exts))
		return 0;

	for (i = 0; i < exts->nr_actions; i++) {
		a = exts->actions[i];
		if (!a->ops->get_dev)
			continue;
		dev = a->ops->get_dev(a);
		if (!dev)
			continue;
		ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop);
		if (ret < 0)
			return ret;
		ok_count += ret;
	}
#endif
	return ok_count;
}

int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
		     enum tc_setup_type type, void *type_data, bool err_stop)
{
	int ok_count;
	int ret;

	ret = tcf_block_cb_call(block, type, type_data, err_stop);
	if (ret < 0)
		return ret;
	ok_count = ret;

	if (!exts || ok_count)
		return ok_count;
	ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
	if (ret < 0)
		return ret;
	ok_count += ret;

	return ok_count;
}
EXPORT_SYMBOL(tc_setup_cb_call);

static __net_init int tcf_net_init(struct net *net)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	idr_init(&tn->idr);
	return 0;
}

static void __net_exit tcf_net_exit(struct net *net)
{
	struct tcf_net *tn = net_generic(net, tcf_net_id);

	idr_destroy(&tn->idr);
}

static struct pernet_operations tcf_net_ops = {
	.init = tcf_net_init,
	.exit = tcf_net_exit,
	.id   = &tcf_net_id,
	.size = sizeof(struct tcf_net),
};

static int __init tc_filter_init(void)
{
	int err;

	tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0);
	if (!tc_filter_wq)
		return -ENOMEM;

	err = register_pernet_subsys(&tcf_net_ops);
	if (err)
		goto err_register_pernet_subsys;

	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
		      tc_dump_tfilter, 0);
	rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain,
		      tc_dump_chain, 0);

	return 0;

err_register_pernet_subsys:
	destroy_workqueue(tc_filter_wq);
	return err;
}

subsys_initcall(tc_filter_init);