Merge branch 'net-sched-multichain-filters'

Jiri Pirko says:

====================
net: sched: introduce multichain support for filters

Currently, each classful qdisc holds one chain of filters.
This chain is traversed and each filter could be matched on, which
may lead to execution of list of actions. One of such action
could be "reclassify", which would "reset" the processing of the
filter chain.

So this filter chain could be looked at as a flat table.
Sometimes it is convenient for user to configure a hierarchy
of tables. Example usecase is encapsulation.

Hierarchy of tables is a common way how it is done in HW pipelines.
So it is much more convenient to offload this.

This patchset contains two major patches:
8/10 - This patch introduces the support for having multiple
       chains of filters.
10/10 - This patch adds new control action to allow going to specified chain

The rest of the patches are smaller or bigger depencies of those 2.
Please see individual patch descriptions for details.

Corresponding iproute2 patches are appended as a reply to this cover letter.

Simple example:
$ tc qdisc add dev eth0 ingress
$ tc filter add dev eth0 parent ffff: protocol ip pref 33 flower dst_mac 52:54:00:3d:c7:6d action goto chain 11
$ tc filter add dev eth0 parent ffff: protocol ip pref 22 chain 11 flower dst_ip 192.168.40.1 action drop
$ tc filter show dev eth0 root
filter parent ffff: protocol ip pref 33 flower chain 0
filter parent ffff: protocol ip pref 33 flower chain 0 handle 0x1
  dst_mac 52:54:00:3d:c7:6d
  eth_type ipv4
        action order 1: gact action goto chain 11
         random type none pass val 0
         index 2 ref 1 bind 1

filter parent ffff: protocol ip pref 22 flower chain 11
filter parent ffff: protocol ip pref 22 flower chain 11 handle 0x1
  eth_type ipv4
  dst_ip 192.168.40.1
        action order 1: gact action drop
         random type none pass val 0
         index 3 ref 1 bind 1
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/act_api.h

@@ -42,6 +42,7 @@ struct tc_action {
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	struct gnet_stats_queue __percpu *cpu_qstats;
 	struct tc_cookie	*act_cookie;
+	struct tcf_chain	*goto_chain;
 };
 #define tcf_head	common.tcfa_head
 #define tcf_index	common.tcfa_index
@@ -180,12 +181,12 @@ int tcf_unregister_action(struct tc_action_ops *a,
 int tcf_action_destroy(struct list_head *actions, int bind);
 int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 		    int nr_actions, struct tcf_result *res);
-int tcf_action_init(struct net *net, struct nlattr *nla,
-				  struct nlattr *est, char *n, int ovr,
-				  int bind, struct list_head *);
-struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
-				    struct nlattr *est, char *n, int ovr,
-				    int bind);
+int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
+		    struct nlattr *est, char *name, int ovr, int bind,
+		    struct list_head *actions);
+struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
+				    struct nlattr *nla, struct nlattr *est,
+				    char *name, int ovr, int bind);
 int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);

include/net/pkt_cls.h

@@ -18,10 +18,30 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops);
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
 
 #ifdef CONFIG_NET_CLS
-void tcf_destroy_chain(struct tcf_proto __rcu **fl);
+struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index);
+void tcf_chain_put(struct tcf_chain *chain);
+int tcf_block_get(struct tcf_block **p_block,
+		  struct tcf_proto __rcu **p_filter_chain);
+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);
+
 #else
-static inline void tcf_destroy_chain(struct tcf_proto __rcu **fl)
+static inline
+int tcf_block_get(struct tcf_block **p_block,
+		  struct tcf_proto __rcu **p_filter_chain)
+{
+	return 0;
+}
+
+static inline void tcf_block_put(struct tcf_block *block)
+{
+}
+
+static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+			       struct tcf_result *res, bool compat_mode)
 {
+	return TC_ACT_UNSPEC;
 }
 #endif
 

include/net/pkt_sched.h

@@ -113,9 +113,6 @@ static inline void qdisc_run(struct Qdisc *q)
 		__qdisc_run(q);
 }
 
-int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
-		struct tcf_result *res, bool compat_mode);
-
 static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
 {
 	/* We need to take extra care in case the skb came via

include/net/sch_generic.h

@@ -8,6 +8,7 @@
 #include <linux/pkt_cls.h>
 #include <linux/percpu.h>
 #include <linux/dynamic_queue_limits.h>
+#include <linux/list.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 
@@ -153,7 +154,7 @@ struct Qdisc_class_ops {
 	void			(*walk)(struct Qdisc *, struct qdisc_walker * arg);
 
 	/* Filter manipulation */
-	struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long);
+	struct tcf_block *	(*tcf_block)(struct Qdisc *, unsigned long);
 	bool			(*tcf_cl_offload)(u32 classid);
 	unsigned long		(*bind_tcf)(struct Qdisc *, unsigned long,
 					u32 classid);
@@ -192,8 +193,13 @@ struct Qdisc_ops {
 
 
 struct tcf_result {
-	unsigned long	class;
-	u32		classid;
+	union {
+		struct {
+			unsigned long	class;
+			u32		classid;
+		};
+		const struct tcf_proto *goto_tp;
+	};
 };
 
 struct tcf_proto_ops {
@@ -236,6 +242,7 @@ struct tcf_proto {
 	struct Qdisc		*q;
 	void			*data;
 	const struct tcf_proto_ops	*ops;
+	struct tcf_chain	*chain;
 	struct rcu_head		rcu;
 };
 
@@ -247,6 +254,19 @@ struct qdisc_skb_cb {
 	unsigned char		data[QDISC_CB_PRIV_LEN];
 };
 
+struct tcf_chain {
+	struct tcf_proto __rcu *filter_chain;
+	struct tcf_proto __rcu **p_filter_chain;
+	struct list_head list;
+	struct tcf_block *block;
+	u32 index; /* chain index */
+	unsigned int refcnt;
+};
+
+struct tcf_block {
+	struct list_head chain_list;
+};
+
 static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 {
 	struct qdisc_skb_cb *qcb;

include/uapi/linux/pkt_cls.h

@@ -51,6 +51,7 @@ enum {
 	(((combined) & (~TC_ACT_EXT_VAL_MASK)) == opcode)
 
 #define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
 
 /* Action type identifiers*/
 enum {

include/uapi/linux/rtnetlink.h

@@ -549,6 +549,7 @@ enum {
 	TCA_STAB,
 	TCA_PAD,
 	TCA_DUMP_INVISIBLE,
+	TCA_CHAIN,
 	__TCA_MAX
 };
 

net/core/dev.c

@@ -105,6 +105,7 @@
 #include <net/dst.h>
 #include <net/dst_metadata.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
 #include <linux/highmem.h>
@@ -3178,7 +3179,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
 	qdisc_bstats_cpu_update(cl->q, skb);
 
-	switch (tc_classify(skb, cl, &cl_res, false)) {
+	switch (tcf_classify(skb, cl, &cl_res, false)) {
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
 		skb->tc_index = TC_H_MIN(cl_res.classid);
@@ -3948,7 +3949,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	skb->tc_at_ingress = 1;
 	qdisc_bstats_cpu_update(cl->q, skb);
 
-	switch (tc_classify(skb, cl, &cl_res, false)) {
+	switch (tcf_classify(skb, cl, &cl_res, false)) {
 	case TC_ACT_OK:
 	case TC_ACT_RECLASSIFY:
 		skb->tc_index = TC_H_MIN(cl_res.classid);

net/sched/act_api.c

@@ -28,6 +28,31 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
+static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp)
+{
+	u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK;
+
+	if (!tp)
+		return -EINVAL;
+	a->goto_chain = tcf_chain_get(tp->chain->block, chain_index);
+	if (!a->goto_chain)
+		return -ENOMEM;
+	return 0;
+}
+
+static void tcf_action_goto_chain_fini(struct tc_action *a)
+{
+	tcf_chain_put(a->goto_chain);
+}
+
+static void tcf_action_goto_chain_exec(const struct tc_action *a,
+				       struct tcf_result *res)
+{
+	const struct tcf_chain *chain = a->goto_chain;
+
+	res->goto_tp = rcu_dereference_bh(chain->filter_chain);
+}
+
 static void free_tcf(struct rcu_head *head)
 {
 	struct tc_action *p = container_of(head, struct tc_action, tcfa_rcu);
@@ -39,6 +64,8 @@ static void free_tcf(struct rcu_head *head)
 		kfree(p->act_cookie->data);
 		kfree(p->act_cookie);
 	}
+	if (p->goto_chain)
+		tcf_action_goto_chain_fini(p);
 
 	kfree(p);
 }
@@ -465,6 +492,8 @@ repeat:
 				else /* faulty graph, stop pipeline */
 					return TC_ACT_OK;
 			}
+		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
+			tcf_action_goto_chain_exec(a, res);
 		}
 
 		if (ret != TC_ACT_PIPE)
@@ -570,9 +599,9 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 	return c;
 }
 
-struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
-				    struct nlattr *est, char *name, int ovr,
-				    int bind)
+struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
+				    struct nlattr *nla, struct nlattr *est,
+				    char *name, int ovr, int bind)
 {
 	struct tc_action *a;
 	struct tc_action_ops *a_o;
@@ -657,6 +686,17 @@ struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
 	if (err != ACT_P_CREATED)
 		module_put(a_o->owner);
 
+	if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
+		err = tcf_action_goto_chain_init(a, tp);
+		if (err) {
+			LIST_HEAD(actions);
+
+			list_add_tail(&a->list, &actions);
+			tcf_action_destroy(&actions, bind);
+			return ERR_PTR(err);
+		}
+	}
+
 	return a;
 
 err_mod:
@@ -680,8 +720,9 @@ static void cleanup_a(struct list_head *actions, int ovr)
 		a->tcfa_refcnt--;
 }
 
-int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est,
-		    char *name, int ovr, int bind, struct list_head *actions)
+int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
+		    struct nlattr *est, char *name, int ovr, int bind,
+		    struct list_head *actions)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
@@ -693,7 +734,7 @@ int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 		return err;
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
-		act = tcf_action_init_1(net, tb[i], est, name, ovr, bind);
+		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind);
 		if (IS_ERR(act)) {
 			err = PTR_ERR(act);
 			goto err;
@@ -1020,7 +1061,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 	int ret = 0;
 	LIST_HEAD(actions);
 
-	ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions);
+	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions);
 	if (ret)
 		return ret;
 

net/sched/cls_api.c

@@ -106,13 +106,12 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 
 static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
 				 struct nlmsghdr *n,
-				 struct tcf_proto __rcu **chain, int event)
+				 struct tcf_chain *chain, int event)
 {
-	struct tcf_proto __rcu **it_chain;
 	struct tcf_proto *tp;
 
-	for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL;
-	     it_chain = &tp->next)
+	for (tp = rtnl_dereference(chain->filter_chain);
+	     tp; tp = rtnl_dereference(tp->next))
 		tfilter_notify(net, oskb, n, tp, 0, event, false);
 }
 
@@ -125,11 +124,12 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
 	if (tp)
 		first = tp->prio - 1;
 
-	return first;
+	return TC_H_MAJ(first);
 }
 
 static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
-					  u32 prio, u32 parent, struct Qdisc *q)
+					  u32 prio, u32 parent, struct Qdisc *q,
+					  struct tcf_chain *chain)
 {
 	struct tcf_proto *tp;
 	int err;
@@ -165,6 +165,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
 	tp->prio = prio;
 	tp->classid = parent;
 	tp->q = q;
+	tp->chain = chain;
 
 	err = tp->ops->init(tp);
 	if (err) {
@@ -185,16 +186,213 @@ static void tcf_proto_destroy(struct tcf_proto *tp)
 	kfree_rcu(tp, rcu);
 }
 
-void tcf_destroy_chain(struct tcf_proto __rcu **fl)
+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;
+	return chain;
+}
+
+static void tcf_chain_destroy(struct tcf_chain *chain)
 {
 	struct tcf_proto *tp;
 
-	while ((tp = rtnl_dereference(*fl)) != NULL) {
-		RCU_INIT_POINTER(*fl, tp->next);
+	list_del(&chain->list);
+	while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) {
+		RCU_INIT_POINTER(chain->filter_chain, tp->next);
 		tcf_proto_destroy(tp);
 	}
+	kfree(chain);
+}
+
+struct tcf_chain *tcf_chain_get(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) {
+			chain->refcnt++;
+			return chain;
+		}
+	}
+	return tcf_chain_create(block, chain_index);
+}
+EXPORT_SYMBOL(tcf_chain_get);
+
+void tcf_chain_put(struct tcf_chain *chain)
+{
+	/* Destroy unused chain, with exception of chain 0, which is the
+	 * default one and has to be always present.
+	 */
+	if (--chain->refcnt == 0 && !chain->filter_chain && chain->index != 0)
+		tcf_chain_destroy(chain);
+}
+EXPORT_SYMBOL(tcf_chain_put);
+
+static void
+tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
+			       struct tcf_proto __rcu **p_filter_chain)
+{
+	chain->p_filter_chain = p_filter_chain;
+}
+
+int tcf_block_get(struct tcf_block **p_block,
+		  struct tcf_proto __rcu **p_filter_chain)
+{
+	struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
+	struct tcf_chain *chain;
+	int err;
+
+	if (!block)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&block->chain_list);
+	/* Create chain 0 by default, it has to be always present. */
+	chain = tcf_chain_create(block, 0);
+	if (!chain) {
+		err = -ENOMEM;
+		goto err_chain_create;
+	}
+	tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
+	*p_block = block;
+	return 0;
+
+err_chain_create:
+	kfree(block);
+	return err;
+}
+EXPORT_SYMBOL(tcf_block_get);
+
+void tcf_block_put(struct tcf_block *block)
+{
+	struct tcf_chain *chain, *tmp;
+
+	if (!block)
+		return;
+
+	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+		tcf_chain_destroy(chain);
+	kfree(block);
+}
+EXPORT_SYMBOL(tcf_block_put);
+
+/* 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 *old_tp = 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)) {
+			goto reset;
+		} else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) {
+			old_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("%s: reclassify loop, rule prio %u, protocol %02x\n",
+				       tp->q->ops->id, tp->prio & 0xffff,
+				       ntohs(tp->protocol));
+		return TC_ACT_SHOT;
+	}
+
+	tp = old_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->p_filter_chain &&
+	    *chain_info->pprev == chain->filter_chain)
+		*chain->p_filter_chain = tp;
+	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
+	rcu_assign_pointer(*chain_info->pprev, tp);
+}
+
+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 (chain->p_filter_chain && tp == chain->filter_chain)
+		*chain->p_filter_chain = next;
+	RCU_INIT_POINTER(*chain_info->pprev, next);
+}
+
+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;
 }
-EXPORT_SYMBOL(tcf_destroy_chain);
 
 /* Add/change/delete/get a filter node */
 
@@ -206,13 +404,14 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	struct tcmsg *t;
 	u32 protocol;
 	u32 prio;
-	u32 nprio;
+	bool prio_allocate;
 	u32 parent;
+	u32 chain_index;
 	struct net_device *dev;
 	struct Qdisc  *q;
-	struct tcf_proto __rcu **back;
-	struct tcf_proto __rcu **chain;
-	struct tcf_proto *next;
+	struct tcf_chain_info chain_info;
+	struct tcf_chain *chain = NULL;
+	struct tcf_block *block;
 	struct tcf_proto *tp;
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
@@ -234,7 +433,7 @@ replay:
 	t = nlmsg_data(n);
 	protocol = TC_H_MIN(t->tcm_info);
 	prio = TC_H_MAJ(t->tcm_info);
-	nprio = prio;
+	prio_allocate = false;
 	parent = t->tcm_parent;
 	cl = 0;
 
@@ -250,6 +449,7 @@ replay:
 			 */
 			if (n->nlmsg_flags & NLM_F_CREATE) {
 				prio = TC_H_MAKE(0x80000000U, 0U);
+				prio_allocate = true;
 				break;
 			}
 			/* fall-through */
@@ -280,7 +480,7 @@ replay:
 	if (!cops)
 		return -EINVAL;
 
-	if (cops->tcf_chain == NULL)
+	if (!cops->tcf_block)
 		return -EOPNOTSUPP;
 
 	/* Do we search for filter, attached to class? */
@@ -291,34 +491,35 @@ replay:
 	}
 
 	/* And the last stroke */
-	chain = cops->tcf_chain(q, cl);
-	if (chain == NULL) {
+	block = cops->tcf_block(q, cl);
+	if (!block) {
+		err = -EINVAL;
+		goto errout;
+	}
+
+	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+	if (chain_index > TC_ACT_EXT_VAL_MASK) {
 		err = -EINVAL;
 		goto errout;
 	}
+	chain = tcf_chain_get(block, chain_index);
+	if (!chain) {
+		err = -ENOMEM;
+		goto errout;
+	}
+
 	if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
 		tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER);
-		tcf_destroy_chain(chain);
+		tcf_chain_destroy(chain);
 		err = 0;
 		goto errout;
 	}
 
-	/* Check the chain for existence of proto-tcf with this priority */
-	for (back = chain;
-	     (tp = rtnl_dereference(*back)) != NULL;
-	     back = &tp->next) {
-		if (tp->prio >= prio) {
-			if (tp->prio == prio) {
-				if (!nprio ||
-				    (tp->protocol != protocol && protocol)) {
-					err = -EINVAL;
-					goto errout;
-				}
-			} else {
-				tp = NULL;
-			}
-			break;
-		}
+	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
+			       prio, prio_allocate);
+	if (IS_ERR(tp)) {
+		err = PTR_ERR(tp);
+		goto errout;
 	}
 
 	if (tp == NULL) {
@@ -335,11 +536,11 @@ replay:
 			goto errout;
 		}
 
-		if (!nprio)
-			nprio = TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back)));
+		if (prio_allocate)
+			prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info));
 
 		tp = tcf_proto_create(nla_data(tca[TCA_KIND]),
-				      protocol, nprio, parent, q);
+				      protocol, prio, parent, q, chain);
 		if (IS_ERR(tp)) {
 			err = PTR_ERR(tp);
 			goto errout;
@@ -354,8 +555,7 @@ replay:
 
 	if (fh == 0) {
 		if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
-			next = rtnl_dereference(tp->next);
-			RCU_INIT_POINTER(*back, next);
+			tcf_chain_tp_remove(chain, &chain_info, tp);
 			tfilter_notify(net, skb, n, tp, fh,
 				       RTM_DELTFILTER, false);
 			tcf_proto_destroy(tp);
@@ -384,11 +584,10 @@ replay:
 			err = tp->ops->delete(tp, fh, &last);
 			if (err)
 				goto errout;
-			next = rtnl_dereference(tp->next);
 			tfilter_notify(net, skb, n, tp, t->tcm_handle,
 				       RTM_DELTFILTER, false);
 			if (last) {
-				RCU_INIT_POINTER(*back, next);
+				tcf_chain_tp_remove(chain, &chain_info, tp);
 				tcf_proto_destroy(tp);
 			}
 			goto errout;
@@ -405,10 +604,8 @@ replay:
 	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);
 	if (err == 0) {
-		if (tp_created) {
-			RCU_INIT_POINTER(tp->next, rtnl_dereference(*back));
-			rcu_assign_pointer(*back, tp);
-		}
+		if (tp_created)
+			tcf_chain_tp_insert(chain, &chain_info, tp);
 		tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false);
 	} else {
 		if (tp_created)
@@ -416,6 +613,8 @@ replay:
 	}
 
 errout:
+	if (chain)
+		tcf_chain_put(chain);
 	if (cl)
 		cops->put(q, cl);
 	if (err == -EAGAIN)
@@ -444,6 +643,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb,
 	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;
 	tcm->tcm_handle = fh;
 	if (RTM_DELTFILTER != event) {
 		tcm->tcm_handle = 0;
@@ -500,22 +701,76 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n,
 			     RTM_NEWTFILTER);
 }
 
+static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb,
+			   struct netlink_callback *cb,
+			   long index_start, long *p_index)
+{
+	struct net *net = sock_net(skb->sk);
+	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, 0,
+					  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.w.stop = 0;
+		arg.w.skip = cb->args[1] - 1;
+		arg.w.count = 0;
+		tp->ops->walk(tp, &arg.w);
+		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);
-	int t;
-	int s_t;
+	struct nlattr *tca[TCA_MAX + 1];
 	struct net_device *dev;
 	struct Qdisc *q;
-	struct tcf_proto *tp, __rcu **chain;
+	struct tcf_block *block;
+	struct tcf_chain *chain;
 	struct tcmsg *tcm = nlmsg_data(cb->nlh);
 	unsigned long cl = 0;
 	const struct Qdisc_class_ops *cops;
-	struct tcf_dump_args arg;
+	long index_start;
+	long index;
+	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;
+
 	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
 	if (!dev)
 		return skb->len;
@@ -529,56 +784,29 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	cops = q->ops->cl_ops;
 	if (!cops)
 		goto errout;
-	if (cops->tcf_chain == NULL)
+	if (!cops->tcf_block)
 		goto errout;
 	if (TC_H_MIN(tcm->tcm_parent)) {
 		cl = cops->get(q, tcm->tcm_parent);
 		if (cl == 0)
 			goto errout;
 	}
-	chain = cops->tcf_chain(q, cl);
-	if (chain == NULL)
+	block = cops->tcf_block(q, cl);
+	if (!block)
 		goto errout;
 
-	s_t = cb->args[0];
+	index_start = cb->args[0];
+	index = 0;
 
-	for (tp = rtnl_dereference(*chain), t = 0;
-	     tp; tp = rtnl_dereference(tp->next), t++) {
-		if (t < s_t)
-			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)
+	list_for_each_entry(chain, &block->chain_list, list) {
+		if (tca[TCA_CHAIN] &&
+		    nla_get_u32(tca[TCA_CHAIN]) != chain->index)
 			continue;
-		if (t > s_t)
-			memset(&cb->args[1], 0,
-			       sizeof(cb->args)-sizeof(cb->args[0]));
-		if (cb->args[1] == 0) {
-			if (tcf_fill_node(net, skb, tp, 0,
-					  NETLINK_CB(cb->skb).portid,
-					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					  RTM_NEWTFILTER) <= 0)
-				break;
-
-			cb->args[1] = 1;
-		}
-		if (tp->ops->walk == NULL)
-			continue;
-		arg.w.fn = tcf_node_dump;
-		arg.skb = skb;
-		arg.cb = cb;
-		arg.w.stop = 0;
-		arg.w.skip = cb->args[1] - 1;
-		arg.w.count = 0;
-		tp->ops->walk(tp, &arg.w);
-		cb->args[1] = arg.w.count + 1;
-		if (arg.w.stop)
+		if (!tcf_chain_dump(chain, skb, cb, index_start, &index))
 			break;
 	}
 
-	cb->args[0] = t;
+	cb->args[0] = index;
 
 errout:
 	if (cl)
@@ -608,8 +836,9 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 		struct tc_action *act;
 
 		if (exts->police && tb[exts->police]) {
-			act = tcf_action_init_1(net, tb[exts->police], rate_tlv,
-						"police", ovr, TCA_ACT_BIND);
+			act = tcf_action_init_1(net, tp, tb[exts->police],
+						rate_tlv, "police", ovr,
+						TCA_ACT_BIND);
 			if (IS_ERR(act))
 				return PTR_ERR(act);
 
@@ -620,8 +849,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 			LIST_HEAD(actions);
 			int err, i = 0;
 
-			err = tcf_action_init(net, tb[exts->action], rate_tlv,
-					      NULL, ovr, TCA_ACT_BIND,
+			err = tcf_action_init(net, tp, tb[exts->action],
+					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
 					      &actions);
 			if (err)
 				return err;

net/sched/sch_api.c

@@ -163,7 +163,7 @@ int register_qdisc(struct Qdisc_ops *qops)
 		if (!(cops->get && cops->put && cops->walk && cops->leaf))
 			goto out_einval;
 
-		if (cops->tcf_chain && !(cops->bind_tcf && cops->unbind_tcf))
+		if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf))
 			goto out_einval;
 	}
 
@@ -1878,54 +1878,6 @@ done:
 	return skb->len;
 }
 
-/* Main classifier routine: scans classifier chain attached
- * to this qdisc, (optionally) tests for protocol and asks
- * specific classifiers.
- */
-int tc_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 *old_tp = 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))
-			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("%s: reclassify loop, rule prio %u, protocol %02x\n",
-				       tp->q->ops->id, tp->prio & 0xffff,
-				       ntohs(tp->protocol));
-		return TC_ACT_SHOT;
-	}
-
-	tp = old_tp;
-	protocol = tc_skb_protocol(skb);
-	goto reclassify;
-#endif
-}
-EXPORT_SYMBOL(tc_classify);
-
 #ifdef CONFIG_PROC_FS
 static int psched_show(struct seq_file *seq, void *v)
 {

net/sched/sch_atm.c

@@ -43,6 +43,7 @@
 struct atm_flow_data {
 	struct Qdisc		*q;	/* FIFO, TBF, etc. */
 	struct tcf_proto __rcu	*filter_list;
+	struct tcf_block	*block;
 	struct atm_vcc		*vcc;	/* VCC; NULL if VCC is closed */
 	void			(*old_pop)(struct atm_vcc *vcc,
 					   struct sk_buff *skb); /* chaining */
@@ -143,7 +144,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl)
 	list_del_init(&flow->list);
 	pr_debug("atm_tc_put: qdisc %p\n", flow->q);
 	qdisc_destroy(flow->q);
-	tcf_destroy_chain(&flow->filter_list);
+	tcf_block_put(flow->block);
 	if (flow->sock) {
 		pr_debug("atm_tc_put: f_count %ld\n",
 			file_count(flow->sock->file));
@@ -274,7 +275,13 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
 		error = -ENOBUFS;
 		goto err_out;
 	}
-	RCU_INIT_POINTER(flow->filter_list, NULL);
+
+	error = tcf_block_get(&flow->block, &flow->filter_list);
+	if (error) {
+		kfree(flow);
+		goto err_out;
+	}
+
 	flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid);
 	if (!flow->q)
 		flow->q = &noop_qdisc;
@@ -346,14 +353,13 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 	}
 }
 
-static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch,
-						unsigned long cl)
+static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
 	struct atm_flow_data *flow = (struct atm_flow_data *)cl;
 
 	pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow);
-	return flow ? &flow->filter_list : &p->link.filter_list;
+	return flow ? flow->block : p->link.block;
 }
 
 /* --------------------------- Qdisc operations ---------------------------- */
@@ -377,7 +383,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		list_for_each_entry(flow, &p->flows, list) {
 			fl = rcu_dereference_bh(flow->filter_list);
 			if (fl) {
-				result = tc_classify(skb, fl, &res, true);
+				result = tcf_classify(skb, fl, &res, true);
 				if (result < 0)
 					continue;
 				flow = (struct atm_flow_data *)res.class;
@@ -524,6 +530,7 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch)
 static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
+	int err;
 
 	pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt);
 	INIT_LIST_HEAD(&p->flows);
@@ -534,7 +541,11 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!p->link.q)
 		p->link.q = &noop_qdisc;
 	pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q);
-	RCU_INIT_POINTER(p->link.filter_list, NULL);
+
+	err = tcf_block_get(&p->link.block, &p->link.filter_list);
+	if (err)
+		return err;
+
 	p->link.vcc = NULL;
 	p->link.sock = NULL;
 	p->link.classid = sch->handle;
@@ -561,7 +572,7 @@ static void atm_tc_destroy(struct Qdisc *sch)
 
 	pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p);
 	list_for_each_entry(flow, &p->flows, list)
-		tcf_destroy_chain(&flow->filter_list);
+		tcf_block_put(flow->block);
 
 	list_for_each_entry_safe(flow, tmp, &p->flows, list) {
 		if (flow->ref > 1)
@@ -646,7 +657,7 @@ static const struct Qdisc_class_ops atm_class_ops = {
 	.change		= atm_tc_change,
 	.delete		= atm_tc_delete,
 	.walk		= atm_tc_walk,
-	.tcf_chain	= atm_tc_find_tcf,
+	.tcf_block	= atm_tc_tcf_block,
 	.bind_tcf	= atm_tc_bind_filter,
 	.unbind_tcf	= atm_tc_put,
 	.dump		= atm_tc_dump_class,

net/sched/sch_cbq.c

@@ -127,6 +127,7 @@ struct cbq_class {
 	struct tc_cbq_xstats	xstats;
 
 	struct tcf_proto __rcu	*filter_list;
+	struct tcf_block	*block;
 
 	int			refcnt;
 	int			filters;
@@ -233,7 +234,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		/*
 		 * Step 2+n. Apply classifier.
 		 */
-		result = tc_classify(skb, fl, &res, true);
+		result = tcf_classify(skb, fl, &res, true);
 		if (!fl || result < 0)
 			goto fallback;
 
@@ -1405,7 +1406,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
 
 	WARN_ON(cl->filters);
 
-	tcf_destroy_chain(&cl->filter_list);
+	tcf_block_put(cl->block);
 	qdisc_destroy(cl->q);
 	qdisc_put_rtab(cl->R_tab);
 	gen_kill_estimator(&cl->rate_est);
@@ -1430,7 +1431,7 @@ static void cbq_destroy(struct Qdisc *sch)
 	 */
 	for (h = 0; h < q->clhash.hashsize; h++) {
 		hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode)
-			tcf_destroy_chain(&cl->filter_list);
+			tcf_block_put(cl->block);
 	}
 	for (h = 0; h < q->clhash.hashsize; h++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h],
@@ -1585,12 +1586,19 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	if (cl == NULL)
 		goto failure;
 
+	err = tcf_block_get(&cl->block, &cl->filter_list);
+	if (err) {
+		kfree(cl);
+		return err;
+	}
+
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
 					NULL,
 					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err) {
+			tcf_block_put(cl->block);
 			kfree(cl);
 			goto failure;
 		}
@@ -1688,8 +1696,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 	return 0;
 }
 
-static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch,
-					     unsigned long arg)
+static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
@@ -1697,7 +1704,7 @@ static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch,
 	if (cl == NULL)
 		cl = &q->link;
 
-	return &cl->filter_list;
+	return cl->block;
 }
 
 static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent,
@@ -1756,7 +1763,7 @@ static const struct Qdisc_class_ops cbq_class_ops = {
 	.change		=	cbq_change_class,
 	.delete		=	cbq_delete,
 	.walk		=	cbq_walk,
-	.tcf_chain	=	cbq_find_tcf,
+	.tcf_block	=	cbq_tcf_block,
 	.bind_tcf	=	cbq_bind_filter,
 	.unbind_tcf	=	cbq_unbind_filter,
 	.dump		=	cbq_dump_class,

net/sched/sch_drr.c

@@ -36,6 +36,7 @@ struct drr_class {
 struct drr_sched {
 	struct list_head		active;
 	struct tcf_proto __rcu		*filter_list;
+	struct tcf_block		*block;
 	struct Qdisc_class_hash		clhash;
 };
 
@@ -190,15 +191,14 @@ static void drr_put_class(struct Qdisc *sch, unsigned long arg)
 		drr_destroy_class(sch, cl);
 }
 
-static struct tcf_proto __rcu **drr_tcf_chain(struct Qdisc *sch,
-					      unsigned long cl)
+static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct drr_sched *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
 
-	return &q->filter_list;
+	return q->block;
 }
 
 static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent,
@@ -333,7 +333,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	fl = rcu_dereference_bh(q->filter_list);
-	result = tc_classify(skb, fl, &res, false);
+	result = tcf_classify(skb, fl, &res, false);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -431,6 +431,9 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 	struct drr_sched *q = qdisc_priv(sch);
 	int err;
 
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
 	err = qdisc_class_hash_init(&q->clhash);
 	if (err < 0)
 		return err;
@@ -462,7 +465,7 @@ static void drr_destroy_qdisc(struct Qdisc *sch)
 	struct hlist_node *next;
 	unsigned int i;
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
@@ -477,7 +480,7 @@ static const struct Qdisc_class_ops drr_class_ops = {
 	.delete		= drr_delete_class,
 	.get		= drr_get_class,
 	.put		= drr_put_class,
-	.tcf_chain	= drr_tcf_chain,
+	.tcf_block	= drr_tcf_block,
 	.bind_tcf	= drr_bind_tcf,
 	.unbind_tcf	= drr_unbind_tcf,
 	.graft		= drr_graft_class,

net/sched/sch_dsmark.c

@@ -44,6 +44,7 @@ struct mask_value {
 struct dsmark_qdisc_data {
 	struct Qdisc		*q;
 	struct tcf_proto __rcu	*filter_list;
+	struct tcf_block	*block;
 	struct mask_value	*mv;
 	u16			indices;
 	u8			set_tc_index;
@@ -183,11 +184,11 @@ ignore:
 	}
 }
 
-static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch,
-						       unsigned long cl)
+static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
-	return &p->filter_list;
+
+	return p->block;
 }
 
 /* --------------------------- Qdisc operations ---------------------------- */
@@ -234,7 +235,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	else {
 		struct tcf_result res;
 		struct tcf_proto *fl = rcu_dereference_bh(p->filter_list);
-		int result = tc_classify(skb, fl, &res, false);
+		int result = tcf_classify(skb, fl, &res, false);
 
 		pr_debug("result %d class 0x%04x\n", result, res.classid);
 
@@ -332,7 +333,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	struct nlattr *tb[TCA_DSMARK_MAX + 1];
-	int err = -EINVAL;
+	int err;
 	u32 default_index = NO_DEFAULT_INDEX;
 	u16 indices;
 	int i;
@@ -342,6 +343,10 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		goto errout;
 
+	err = tcf_block_get(&p->block, &p->filter_list);
+	if (err)
+		return err;
+
 	err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL);
 	if (err < 0)
 		goto errout;
@@ -400,7 +405,7 @@ static void dsmark_destroy(struct Qdisc *sch)
 
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 
-	tcf_destroy_chain(&p->filter_list);
+	tcf_block_put(p->block);
 	qdisc_destroy(p->q);
 	if (p->mv != p->embedded)
 		kfree(p->mv);
@@ -468,7 +473,7 @@ static const struct Qdisc_class_ops dsmark_class_ops = {
 	.change		=	dsmark_change,
 	.delete		=	dsmark_delete,
 	.walk		=	dsmark_walk,
-	.tcf_chain	=	dsmark_find_tcf,
+	.tcf_block	=	dsmark_tcf_block,
 	.bind_tcf	=	dsmark_bind_filter,
 	.unbind_tcf	=	dsmark_put,
 	.dump		=	dsmark_dump_class,

net/sched/sch_fq_codel.c

@@ -55,6 +55,7 @@ struct fq_codel_flow {
 
 struct fq_codel_sched_data {
 	struct tcf_proto __rcu *filter_list; /* optional external classifier */
+	struct tcf_block *block;
 	struct fq_codel_flow *flows;	/* Flows table [flows_cnt] */
 	u32		*backlogs;	/* backlog table [flows_cnt] */
 	u32		flows_cnt;	/* number of flows */
@@ -96,7 +97,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 		return fq_codel_hash(q, skb) + 1;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tc_classify(skb, filter, &res, false);
+	result = tcf_classify(skb, filter, &res, false);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -450,7 +451,7 @@ static void fq_codel_destroy(struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 	kvfree(q->backlogs);
 	kvfree(q->flows);
 }
@@ -459,6 +460,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	int i;
+	int err;
 
 	sch->limit = 10*1024;
 	q->flows_cnt = 1024;
@@ -478,6 +480,10 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
 			return err;
 	}
 
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
+
 	if (!q->flows) {
 		q->flows = kvzalloc(q->flows_cnt *
 					   sizeof(struct fq_codel_flow), GFP_KERNEL);
@@ -589,14 +595,13 @@ static void fq_codel_put(struct Qdisc *q, unsigned long cl)
 {
 }
 
-static struct tcf_proto __rcu **fq_codel_find_tcf(struct Qdisc *sch,
-						  unsigned long cl)
+static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
-	return &q->filter_list;
+	return q->block;
 }
 
 static int fq_codel_dump_class(struct Qdisc *sch, unsigned long cl,
@@ -679,7 +684,7 @@ static const struct Qdisc_class_ops fq_codel_class_ops = {
 	.leaf		=	fq_codel_leaf,
 	.get		=	fq_codel_get,
 	.put		=	fq_codel_put,
-	.tcf_chain	=	fq_codel_find_tcf,
+	.tcf_block	=	fq_codel_tcf_block,
 	.bind_tcf	=	fq_codel_bind,
 	.unbind_tcf	=	fq_codel_put,
 	.dump		=	fq_codel_dump_class,

net/sched/sch_hfsc.c

@@ -116,6 +116,7 @@ struct hfsc_class {
 	struct gnet_stats_queue qstats;
 	struct net_rate_estimator __rcu *rate_est;
 	struct tcf_proto __rcu *filter_list; /* filter list */
+	struct tcf_block *block;
 	unsigned int	filter_cnt;	/* filter count */
 	unsigned int	level;		/* class level in hierarchy */
 
@@ -1040,12 +1041,19 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	if (cl == NULL)
 		return -ENOBUFS;
 
+	err = tcf_block_get(&cl->block, &cl->filter_list);
+	if (err) {
+		kfree(cl);
+		return err;
+	}
+
 	if (tca[TCA_RATE]) {
 		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
 					NULL,
 					qdisc_root_sleeping_running(sch),
 					tca[TCA_RATE]);
 		if (err) {
+			tcf_block_put(cl->block);
 			kfree(cl);
 			return err;
 		}
@@ -1091,7 +1099,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl)
 {
 	struct hfsc_sched *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&cl->filter_list);
+	tcf_block_put(cl->block);
 	qdisc_destroy(cl->qdisc);
 	gen_kill_estimator(&cl->rate_est);
 	if (cl != &q->root)
@@ -1142,7 +1150,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	head = &q->root;
 	tcf = rcu_dereference_bh(q->root.filter_list);
-	while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) {
+	while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
 		case TC_ACT_QUEUED:
@@ -1261,8 +1269,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg)
 	cl->filter_cnt--;
 }
 
-static struct tcf_proto __rcu **
-hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg)
+static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg)
 {
 	struct hfsc_sched *q = qdisc_priv(sch);
 	struct hfsc_class *cl = (struct hfsc_class *)arg;
@@ -1270,7 +1277,7 @@ hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg)
 	if (cl == NULL)
 		cl = &q->root;
 
-	return &cl->filter_list;
+	return cl->block;
 }
 
 static int
@@ -1515,7 +1522,7 @@ hfsc_destroy_qdisc(struct Qdisc *sch)
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode)
-			tcf_destroy_chain(&cl->filter_list);
+			tcf_block_put(cl->block);
 	}
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
@@ -1662,7 +1669,7 @@ static const struct Qdisc_class_ops hfsc_class_ops = {
 	.put		= hfsc_put_class,
 	.bind_tcf	= hfsc_bind_tcf,
 	.unbind_tcf	= hfsc_unbind_tcf,
-	.tcf_chain	= hfsc_tcf_chain,
+	.tcf_block	= hfsc_tcf_block,
 	.dump		= hfsc_dump_class,
 	.dump_stats	= hfsc_dump_class_stats,
 	.walk		= hfsc_walk

net/sched/sch_htb.c

@@ -105,6 +105,7 @@ struct htb_class {
 	int			quantum;	/* but stored for parent-to-leaf return */
 
 	struct tcf_proto __rcu	*filter_list;	/* class attached filters */
+	struct tcf_block	*block;
 	int			filter_cnt;
 	int			refcnt;		/* usage count of this class */
 
@@ -156,6 +157,7 @@ struct htb_sched {
 
 	/* filters for qdisc itself */
 	struct tcf_proto __rcu	*filter_list;
+	struct tcf_block	*block;
 
 #define HTB_WARN_TOOMANYEVENTS	0x1
 	unsigned int		warned;	/* only one warning */
@@ -231,7 +233,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) {
+	while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
 		case TC_ACT_QUEUED:
@@ -1017,6 +1019,10 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt)
 	if (!opt)
 		return -EINVAL;
 
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
+
 	err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL);
 	if (err < 0)
 		return err;
@@ -1230,7 +1236,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
 		qdisc_destroy(cl->un.leaf.q);
 	}
 	gen_kill_estimator(&cl->rate_est);
-	tcf_destroy_chain(&cl->filter_list);
+	tcf_block_put(cl->block);
 	kfree(cl);
 }
 
@@ -1248,11 +1254,11 @@ static void htb_destroy(struct Qdisc *sch)
 	 * because filter need its target class alive to be able to call
 	 * unbind_filter on it (without Oops).
 	 */
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode)
-			tcf_destroy_chain(&cl->filter_list);
+			tcf_block_put(cl->block);
 	}
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
@@ -1396,6 +1402,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		if (!cl)
 			goto failure;
 
+		err = tcf_block_get(&cl->block, &cl->filter_list);
+		if (err) {
+			kfree(cl);
+			goto failure;
+		}
 		if (htb_rate_est || tca[TCA_RATE]) {
 			err = gen_new_estimator(&cl->bstats, NULL,
 						&cl->rate_est,
@@ -1403,6 +1414,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 						qdisc_root_sleeping_running(sch),
 						tca[TCA_RATE] ? : &est.nla);
 			if (err) {
+				tcf_block_put(cl->block);
 				kfree(cl);
 				goto failure;
 			}
@@ -1521,14 +1533,12 @@ failure:
 	return err;
 }
 
-static struct tcf_proto __rcu **htb_find_tcf(struct Qdisc *sch,
-					     unsigned long arg)
+static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)arg;
-	struct tcf_proto __rcu **fl = cl ? &cl->filter_list : &q->filter_list;
 
-	return fl;
+	return cl ? cl->block : q->block;
 }
 
 static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent,
@@ -1591,7 +1601,7 @@ static const struct Qdisc_class_ops htb_class_ops = {
 	.change		=	htb_change_class,
 	.delete		=	htb_delete,
 	.walk		=	htb_walk,
-	.tcf_chain	=	htb_find_tcf,
+	.tcf_block	=	htb_tcf_block,
 	.bind_tcf	=	htb_bind_filter,
 	.unbind_tcf	=	htb_unbind_filter,
 	.dump		=	htb_dump_class,

net/sched/sch_ingress.c

@@ -18,6 +18,10 @@
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
 
+struct ingress_sched_data {
+	struct tcf_block *block;
+};
+
 static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg)
 {
 	return NULL;
@@ -47,16 +51,23 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 {
 }
 
-static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch,
-						 unsigned long cl)
+static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
-	struct net_device *dev = qdisc_dev(sch);
+	struct ingress_sched_data *q = qdisc_priv(sch);
 
-	return &dev->ingress_cl_list;
+	return q->block;
 }
 
 static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 {
+	struct ingress_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	int err;
+
+	err = tcf_block_get(&q->block, &dev->ingress_cl_list);
+	if (err)
+		return err;
+
 	net_inc_ingress_queue();
 	sch->flags |= TCQ_F_CPUSTATS;
 
@@ -65,9 +76,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 
 static void ingress_destroy(struct Qdisc *sch)
 {
-	struct net_device *dev = qdisc_dev(sch);
+	struct ingress_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&dev->ingress_cl_list);
+	tcf_block_put(q->block);
 	net_dec_ingress_queue();
 }
 
@@ -91,7 +102,7 @@ static const struct Qdisc_class_ops ingress_class_ops = {
 	.get		=	ingress_get,
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
-	.tcf_chain	=	ingress_find_tcf,
+	.tcf_block	=	ingress_tcf_block,
 	.tcf_cl_offload	=	ingress_cl_offload,
 	.bind_tcf	=	ingress_bind_filter,
 	.unbind_tcf	=	ingress_put,
@@ -100,12 +111,18 @@ static const struct Qdisc_class_ops ingress_class_ops = {
 static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
 	.cl_ops		=	&ingress_class_ops,
 	.id		=	"ingress",
+	.priv_size	=	sizeof(struct ingress_sched_data),
 	.init		=	ingress_init,
 	.destroy	=	ingress_destroy,
 	.dump		=	ingress_dump,
 	.owner		=	THIS_MODULE,
 };
 
+struct clsact_sched_data {
+	struct tcf_block *ingress_block;
+	struct tcf_block *egress_block;
+};
+
 static unsigned long clsact_get(struct Qdisc *sch, u32 classid)
 {
 	switch (TC_H_MIN(classid)) {
@@ -128,16 +145,15 @@ static unsigned long clsact_bind_filter(struct Qdisc *sch,
 	return clsact_get(sch, classid);
 }
 
-static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch,
-						unsigned long cl)
+static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
-	struct net_device *dev = qdisc_dev(sch);
+	struct clsact_sched_data *q = qdisc_priv(sch);
 
 	switch (cl) {
 	case TC_H_MIN(TC_H_MIN_INGRESS):
-		return &dev->ingress_cl_list;
+		return q->ingress_block;
 	case TC_H_MIN(TC_H_MIN_EGRESS):
-		return &dev->egress_cl_list;
+		return q->egress_block;
 	default:
 		return NULL;
 	}
@@ -145,6 +161,18 @@ static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch,
 
 static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 {
+	struct clsact_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	int err;
+
+	err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list);
+	if (err)
+		return err;
+
+	err = tcf_block_get(&q->egress_block, &dev->egress_cl_list);
+	if (err)
+		return err;
+
 	net_inc_ingress_queue();
 	net_inc_egress_queue();
 
@@ -155,10 +183,10 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 
 static void clsact_destroy(struct Qdisc *sch)
 {
-	struct net_device *dev = qdisc_dev(sch);
+	struct clsact_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&dev->ingress_cl_list);
-	tcf_destroy_chain(&dev->egress_cl_list);
+	tcf_block_put(q->egress_block);
+	tcf_block_put(q->ingress_block);
 
 	net_dec_ingress_queue();
 	net_dec_egress_queue();
@@ -169,7 +197,7 @@ static const struct Qdisc_class_ops clsact_class_ops = {
 	.get		=	clsact_get,
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
-	.tcf_chain	=	clsact_find_tcf,
+	.tcf_block	=	clsact_tcf_block,
 	.tcf_cl_offload	=	clsact_cl_offload,
 	.bind_tcf	=	clsact_bind_filter,
 	.unbind_tcf	=	ingress_put,
@@ -178,6 +206,7 @@ static const struct Qdisc_class_ops clsact_class_ops = {
 static struct Qdisc_ops clsact_qdisc_ops __read_mostly = {
 	.cl_ops		=	&clsact_class_ops,
 	.id		=	"clsact",
+	.priv_size	=	sizeof(struct clsact_sched_data),
 	.init		=	clsact_init,
 	.destroy	=	clsact_destroy,
 	.dump		=	ingress_dump,

net/sched/sch_multiq.c

@@ -32,6 +32,7 @@ struct multiq_sched_data {
 	u16 max_bands;
 	u16 curband;
 	struct tcf_proto __rcu *filter_list;
+	struct tcf_block *block;
 	struct Qdisc **queues;
 };
 
@@ -46,7 +47,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	int err;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	err = tc_classify(skb, fl, &res, false);
+	err = tcf_classify(skb, fl, &res, false);
 #ifdef CONFIG_NET_CLS_ACT
 	switch (err) {
 	case TC_ACT_STOLEN:
@@ -170,7 +171,7 @@ multiq_destroy(struct Qdisc *sch)
 	int band;
 	struct multiq_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 	for (band = 0; band < q->bands; band++)
 		qdisc_destroy(q->queues[band]);
 
@@ -243,6 +244,10 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt)
 	if (opt == NULL)
 		return -EINVAL;
 
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
+
 	q->max_bands = qdisc_dev(sch)->num_tx_queues;
 
 	q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL);
@@ -367,14 +372,13 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 	}
 }
 
-static struct tcf_proto __rcu **multiq_find_tcf(struct Qdisc *sch,
-						unsigned long cl)
+static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct multiq_sched_data *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
-	return &q->filter_list;
+	return q->block;
 }
 
 static const struct Qdisc_class_ops multiq_class_ops = {
@@ -383,7 +387,7 @@ static const struct Qdisc_class_ops multiq_class_ops = {
 	.get		=	multiq_get,
 	.put		=	multiq_put,
 	.walk		=	multiq_walk,
-	.tcf_chain	=	multiq_find_tcf,
+	.tcf_block	=	multiq_tcf_block,
 	.bind_tcf	=	multiq_bind,
 	.unbind_tcf	=	multiq_put,
 	.dump		=	multiq_dump_class,

net/sched/sch_prio.c

@@ -25,6 +25,7 @@
 struct prio_sched_data {
 	int bands;
 	struct tcf_proto __rcu *filter_list;
+	struct tcf_block *block;
 	u8  prio2band[TC_PRIO_MAX+1];
 	struct Qdisc *queues[TCQ_PRIO_BANDS];
 };
@@ -42,7 +43,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	if (TC_H_MAJ(skb->priority) != sch->handle) {
 		fl = rcu_dereference_bh(q->filter_list);
-		err = tc_classify(skb, fl, &res, false);
+		err = tcf_classify(skb, fl, &res, false);
 #ifdef CONFIG_NET_CLS_ACT
 		switch (err) {
 		case TC_ACT_STOLEN:
@@ -145,7 +146,7 @@ prio_destroy(struct Qdisc *sch)
 	int prio;
 	struct prio_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 	for (prio = 0; prio < q->bands; prio++)
 		qdisc_destroy(q->queues[prio]);
 }
@@ -204,9 +205,16 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt)
 
 static int prio_init(struct Qdisc *sch, struct nlattr *opt)
 {
+	struct prio_sched_data *q = qdisc_priv(sch);
+	int err;
+
 	if (!opt)
 		return -EINVAL;
 
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
+
 	return prio_tune(sch, opt);
 }
 
@@ -317,14 +325,13 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 	}
 }
 
-static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch,
-					      unsigned long cl)
+static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct prio_sched_data *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
-	return &q->filter_list;
+	return q->block;
 }
 
 static const struct Qdisc_class_ops prio_class_ops = {
@@ -333,7 +340,7 @@ static const struct Qdisc_class_ops prio_class_ops = {
 	.get		=	prio_get,
 	.put		=	prio_put,
 	.walk		=	prio_walk,
-	.tcf_chain	=	prio_find_tcf,
+	.tcf_block	=	prio_tcf_block,
 	.bind_tcf	=	prio_bind,
 	.unbind_tcf	=	prio_put,
 	.dump		=	prio_dump_class,

net/sched/sch_qfq.c

@@ -182,6 +182,7 @@ struct qfq_group {
 
 struct qfq_sched {
 	struct tcf_proto __rcu *filter_list;
+	struct tcf_block	*block;
 	struct Qdisc_class_hash clhash;
 
 	u64			oldV, V;	/* Precise virtual times. */
@@ -582,15 +583,14 @@ static void qfq_put_class(struct Qdisc *sch, unsigned long arg)
 		qfq_destroy_class(sch, cl);
 }
 
-static struct tcf_proto __rcu **qfq_tcf_chain(struct Qdisc *sch,
-					      unsigned long cl)
+static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
 
-	return &q->filter_list;
+	return q->block;
 }
 
 static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent,
@@ -720,7 +720,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	fl = rcu_dereference_bh(q->filter_list);
-	result = tc_classify(skb, fl, &res, false);
+	result = tcf_classify(skb, fl, &res, false);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -1438,6 +1438,10 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt)
 	int i, j, err;
 	u32 max_cl_shift, maxbudg_shift, max_classes;
 
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
+
 	err = qdisc_class_hash_init(&q->clhash);
 	if (err < 0)
 		return err;
@@ -1492,7 +1496,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch)
 	struct hlist_node *next;
 	unsigned int i;
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
@@ -1508,7 +1512,7 @@ static const struct Qdisc_class_ops qfq_class_ops = {
 	.delete		= qfq_delete_class,
 	.get		= qfq_get_class,
 	.put		= qfq_put_class,
-	.tcf_chain	= qfq_tcf_chain,
+	.tcf_block	= qfq_tcf_block,
 	.bind_tcf	= qfq_bind_tcf,
 	.unbind_tcf	= qfq_unbind_tcf,
 	.graft		= qfq_graft_class,

net/sched/sch_sfb.c

@@ -56,6 +56,7 @@ struct sfb_bins {
 struct sfb_sched_data {
 	struct Qdisc	*qdisc;
 	struct tcf_proto __rcu *filter_list;
+	struct tcf_block *block;
 	unsigned long	rehash_interval;
 	unsigned long	warmup_time;	/* double buffering warmup time in jiffies */
 	u32		max;
@@ -259,7 +260,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
 	struct tcf_result res;
 	int result;
 
-	result = tc_classify(skb, fl, &res, false);
+	result = tcf_classify(skb, fl, &res, false);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -465,7 +466,7 @@ static void sfb_destroy(struct Qdisc *sch)
 {
 	struct sfb_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 	qdisc_destroy(q->qdisc);
 }
 
@@ -549,6 +550,11 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt)
 static int sfb_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct sfb_sched_data *q = qdisc_priv(sch);
+	int err;
+
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
 
 	q->qdisc = &noop_qdisc;
 	return sfb_change(sch, opt);
@@ -657,14 +663,13 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 	}
 }
 
-static struct tcf_proto __rcu **sfb_find_tcf(struct Qdisc *sch,
-					     unsigned long cl)
+static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct sfb_sched_data *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
-	return &q->filter_list;
+	return q->block;
 }
 
 static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent,
@@ -682,7 +687,7 @@ static const struct Qdisc_class_ops sfb_class_ops = {
 	.change		=	sfb_change_class,
 	.delete		=	sfb_delete,
 	.walk		=	sfb_walk,
-	.tcf_chain	=	sfb_find_tcf,
+	.tcf_block	=	sfb_tcf_block,
 	.bind_tcf	=	sfb_bind,
 	.unbind_tcf	=	sfb_put,
 	.dump		=	sfb_dump_class,

net/sched/sch_sfq.c

@@ -126,6 +126,7 @@ struct sfq_sched_data {
 	u8		flags;
 	unsigned short  scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
 	struct tcf_proto __rcu *filter_list;
+	struct tcf_block *block;
 	sfq_index	*ht;		/* Hash table ('divisor' slots) */
 	struct sfq_slot	*slots;		/* Flows table ('maxflows' entries) */
 
@@ -180,7 +181,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 		return sfq_hash(q, skb) + 1;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tc_classify(skb, fl, &res, false);
+	result = tcf_classify(skb, fl, &res, false);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -697,7 +698,7 @@ static void sfq_destroy(struct Qdisc *sch)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 
-	tcf_destroy_chain(&q->filter_list);
+	tcf_block_put(q->block);
 	q->perturb_period = 0;
 	del_timer_sync(&q->perturb_timer);
 	sfq_free(q->ht);
@@ -709,6 +710,11 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	int i;
+	int err;
+
+	err = tcf_block_get(&q->block, &q->filter_list);
+	if (err)
+		return err;
 
 	setup_deferrable_timer(&q->perturb_timer, sfq_perturbation,
 			       (unsigned long)sch);
@@ -815,14 +821,13 @@ static void sfq_put(struct Qdisc *q, unsigned long cl)
 {
 }
 
-static struct tcf_proto __rcu **sfq_find_tcf(struct Qdisc *sch,
-					     unsigned long cl)
+static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 
 	if (cl)
 		return NULL;
-	return &q->filter_list;
+	return q->block;
 }
 
 static int sfq_dump_class(struct Qdisc *sch, unsigned long cl,
@@ -878,7 +883,7 @@ static const struct Qdisc_class_ops sfq_class_ops = {
 	.leaf		=	sfq_leaf,
 	.get		=	sfq_get,
 	.put		=	sfq_put,
-	.tcf_chain	=	sfq_find_tcf,
+	.tcf_block	=	sfq_tcf_block,
 	.bind_tcf	=	sfq_bind,
 	.unbind_tcf	=	sfq_put,
 	.dump		=	sfq_dump_class,