Merge branch 'Refactor-classifier-API-to-work-with-Qdisc-blocks-without-rtnl-lock'

Vlad Buslov says:

====================
Refactor classifier API to work with Qdisc/blocks without rtnl lock

Currently, all netlink protocol handlers for updating rules, actions and
qdiscs are protected with single global rtnl lock which removes any
possibility for parallelism. This patch set is a third step to remove
rtnl lock dependency from TC rules update path.

Recently, new rtnl registration flag RTNL_FLAG_DOIT_UNLOCKED was added.
Handlers registered with this flag are called without RTNL taken. End
goal is to have rule update handlers(RTM_NEWTFILTER, RTM_DELTFILTER,
etc.) to be registered with UNLOCKED flag to allow parallel execution.
However, there is no intention to completely remove or split rtnl lock
itself. This patch set addresses specific problems in implementation of
classifiers API that prevent its control path from being executed
concurrently. Additional changes are required to refactor classifiers
API and individual classifiers for parallel execution. This patch set
lays groundwork to eventually register rule update handlers as
rtnl-unlocked by modifying code in cls API that works with Qdiscs and
blocks. Following patch set does the same for chains and classifiers.

The goal of this change is to refactor tcf_block_find() and its
dependencies to allow concurrent execution:
- Extend Qdisc API with rcu to lookup and take reference to Qdisc
  without relying on rtnl lock.
- Extend tcf_block with atomic reference counting and rcu.
- Always take reference to tcf_block while working with it.
- Implement tcf_block_release() to release resources obtained by
  tcf_block_find()
- Create infrastructure to allow registering Qdiscs with class ops that
  do not require the caller to hold rtnl lock.

All three netlink rule update handlers use tcf_block_find() to lookup
Qdisc and block, and this patch set introduces additional means of
synchronization to substitute rtnl lock in cls API.

Some functions in cls and sch APIs have historic names that no longer
clearly describe their intent. In order not make this code even more
confusing when introducing their concurrency-friendly versions, rename
these functions to describe actual implementation.

Changes from V2 to V3:
- Patch 1:
  - Explicitly include refcount.h in rtnetlink.h.
- Patch 3:
  - Move rcu_head field to the end of struct Qdisc.
  - Rearrange local variable declarations in qdisc_lookup_rcu().
- Patch 5:
  - Remove tcf_qdisc_put() and inline its content to callers.

Changes from V1 to V2:
- Rebase on latest net-next.
- Patch 8 - remove.
- Patch 9 - fold into patch 11.
- Patch 11:
  - Rename tcf_block_{get|put}() to tcf_block_refcnt_{get|put}().
- Patch 13 - remove.
====================

Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

24 files changed, 294 insertions, 112 deletions

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 5225832bd6ff..bb9cb84114c1 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -6,6 +6,7 @@
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/wait.h>
+#include <linux/refcount.h>
 #include <uapi/linux/rtnetlink.h>
 
 extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
@@ -34,6 +35,7 @@ extern void rtnl_unlock(void);
 extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
 extern int rtnl_lock_killable(void);
+extern bool refcount_dec_and_rtnl_lock(refcount_t *r);
 
 extern wait_queue_head_t netdev_unregistering_wq;
 extern struct rw_semaphore pernet_ops_rwsem;
@@ -83,6 +85,11 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
 	return rtnl_dereference(dev->ingress_queue);
 }
 
+static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev)
+{
+	return rcu_dereference(dev->ingress_queue);
+}
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev);
 
 #ifdef CONFIG_NET_INGRESS
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 7dc769e5452b..a16fbe9a2a67 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -102,6 +102,7 @@ int qdisc_set_default(const char *id);
 void qdisc_hash_add(struct Qdisc *q, bool invisible);
 void qdisc_hash_del(struct Qdisc *q);
 struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
+struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle);
 struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
 					struct nlattr *tab,
 					struct netlink_ext_ack *extack);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d326fd553b58..7a6b71ee5433 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -105,6 +105,7 @@ struct Qdisc {
 
 	spinlock_t		busylock ____cacheline_aligned_in_smp;
 	spinlock_t		seqlock;
+	struct rcu_head		rcu;
 };
 
 static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
@@ -114,6 +115,19 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
 	refcount_inc(&qdisc->refcnt);
 }
 
+/* Intended to be used by unlocked users, when concurrent qdisc release is
+ * possible.
+ */
+
+static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc)
+{
+	if (qdisc->flags & TCQ_F_BUILTIN)
+		return qdisc;
+	if (refcount_inc_not_zero(&qdisc->refcnt))
+		return qdisc;
+	return NULL;
+}
+
 static inline bool qdisc_is_running(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK)
@@ -331,7 +345,7 @@ struct tcf_chain {
 struct tcf_block {
 	struct list_head chain_list;
 	u32 index; /* block index for shared blocks */
-	unsigned int refcnt;
+	refcount_t refcnt;
 	struct net *net;
 	struct Qdisc *q;
 	struct list_head cb_list;
@@ -343,6 +357,7 @@ struct tcf_block {
 		struct tcf_chain *chain;
 		struct list_head filter_chain_list;
 	} chain0;
+	struct rcu_head rcu;
 };
 
 static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
@@ -554,7 +569,8 @@ void dev_deactivate_many(struct list_head *head);
 struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
-void qdisc_destroy(struct Qdisc *qdisc);
+void qdisc_put(struct Qdisc *qdisc);
+void qdisc_put_unlocked(struct Qdisc *qdisc);
 void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
 			       unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 80a7e18c65fb..35162e1b06ad 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -130,6 +130,12 @@ int rtnl_is_locked(void)
 }
 EXPORT_SYMBOL(rtnl_is_locked);
 
+bool refcount_dec_and_rtnl_lock(refcount_t *r)
+{
+	return refcount_dec_and_mutex_lock(r, &rtnl_mutex);
+}
+EXPORT_SYMBOL(refcount_dec_and_rtnl_lock);
+
 #ifdef CONFIG_PROVE_LOCKING
 bool lockdep_rtnl_is_held(void)
 {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0a75cb2e5e7b..3de47e99b788 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -240,8 +240,8 @@ static void tcf_chain_destroy(struct tcf_chain *chain)
 	if (!chain->index)
 		block->chain0.chain = NULL;
 	kfree(chain);
-	if (list_empty(&block->chain_list) && block->refcnt == 0)
-		kfree(block);
+	if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt))
+		kfree_rcu(block, rcu);
 }
 
 static void tcf_chain_hold(struct tcf_chain *chain)
@@ -473,6 +473,7 @@ tcf_chain0_head_change_cb_del(struct tcf_block *block,
 }
 
 struct tcf_net {
+	spinlock_t idr_lock; /* Protects idr */
 	struct idr idr;
 };
 
@@ -482,16 +483,25 @@ 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);
+	int err;
+
+	idr_preload(GFP_KERNEL);
+	spin_lock(&tn->idr_lock);
+	err = idr_alloc_u32(&tn->idr, block, &block->index, block->index,
+			    GFP_NOWAIT);
+	spin_unlock(&tn->idr_lock);
+	idr_preload_end();
 
-	return idr_alloc_u32(&tn->idr, block, &block->index, block->index,
-			     GFP_KERNEL);
+	return err;
 }
 
 static void tcf_block_remove(struct tcf_block *block, struct net *net)
 {
 	struct tcf_net *tn = net_generic(net, tcf_net_id);
 
+	spin_lock(&tn->idr_lock);
 	idr_remove(&tn->idr, block->index);
+	spin_unlock(&tn->idr_lock);
 }
 
 static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
@@ -510,7 +520,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	INIT_LIST_HEAD(&block->owner_list);
 	INIT_LIST_HEAD(&block->chain0.filter_chain_list);
 
-	block->refcnt = 1;
+	refcount_set(&block->refcnt, 1);
 	block->net = net;
 	block->index = block_index;
 
@@ -527,6 +537,78 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
 	return idr_find(&tn->idr, block_index);
 }
 
+static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
+{
+	struct tcf_block *block;
+
+	rcu_read_lock();
+	block = tcf_block_lookup(net, block_index);
+	if (block && !refcount_inc_not_zero(&block->refcnt))
+		block = NULL;
+	rcu_read_unlock();
+
+	return block;
+}
+
+static void tcf_block_flush_all_chains(struct tcf_block *block)
+{
+	struct tcf_chain *chain;
+
+	/* 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);
+}
+
+static void tcf_block_put_all_chains(struct tcf_block *block)
+{
+	struct tcf_chain *chain, *tmp;
+
+	/* 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);
+	}
+}
+
+static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q,
+			    struct tcf_block_ext_info *ei)
+{
+	if (refcount_dec_and_test(&block->refcnt)) {
+		/* Flushing/putting all chains will cause the block to be
+		 * deallocated when last chain is freed. However, if chain_list
+		 * is empty, block has to be manually deallocated. After block
+		 * reference counter reached 0, it is no longer possible to
+		 * increment it or add new chains to block.
+		 */
+		bool free_block = list_empty(&block->chain_list);
+
+		if (tcf_block_shared(block))
+			tcf_block_remove(block, block->net);
+		if (!free_block)
+			tcf_block_flush_all_chains(block);
+
+		if (q)
+			tcf_block_offload_unbind(block, q, ei);
+
+		if (free_block)
+			kfree_rcu(block, rcu);
+		else
+			tcf_block_put_all_chains(block);
+	} else if (q) {
+		tcf_block_offload_unbind(block, q, ei);
+	}
+}
+
+static void tcf_block_refcnt_put(struct tcf_block *block)
+{
+	__tcf_block_put(block, NULL, NULL);
+}
+
 /* Find tcf block.
  * Set q, parent, cl when appropriate.
  */
@@ -537,9 +619,10 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
 					struct netlink_ext_ack *extack)
 {
 	struct tcf_block *block;
+	int err = 0;
 
 	if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
-		block = tcf_block_lookup(net, block_index);
+		block = tcf_block_refcnt_get(net, block_index);
 		if (!block) {
 			NL_SET_ERR_MSG(extack, "Block of given index was not found");
 			return ERR_PTR(-EINVAL);
@@ -548,55 +631,104 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
 		const struct Qdisc_class_ops *cops;
 		struct net_device *dev;
 
+		rcu_read_lock();
+
 		/* Find link */
-		dev = __dev_get_by_index(net, ifindex);
-		if (!dev)
+		dev = dev_get_by_index_rcu(net, ifindex);
+		if (!dev) {
+			rcu_read_unlock();
 			return ERR_PTR(-ENODEV);
+		}
 
 		/* Find qdisc */
 		if (!*parent) {
 			*q = dev->qdisc;
 			*parent = (*q)->handle;
 		} else {
-			*q = qdisc_lookup(dev, TC_H_MAJ(*parent));
+			*q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
 			if (!*q) {
 				NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
-				return ERR_PTR(-EINVAL);
+				err = -EINVAL;
+				goto errout_rcu;
 			}
 		}
 
+		*q = qdisc_refcount_inc_nz(*q);
+		if (!*q) {
+			NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
+			err = -EINVAL;
+			goto errout_rcu;
+		}
+
 		/* Is it classful? */
 		cops = (*q)->ops->cl_ops;
 		if (!cops) {
 			NL_SET_ERR_MSG(extack, "Qdisc not classful");
-			return ERR_PTR(-EINVAL);
+			err = -EINVAL;
+			goto errout_rcu;
 		}
 
 		if (!cops->tcf_block) {
 			NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
-			return ERR_PTR(-EOPNOTSUPP);
+			err = -EOPNOTSUPP;
+			goto errout_rcu;
 		}
 
+		/* At this point we know that qdisc is not noop_qdisc,
+		 * which means that qdisc holds a reference to net_device
+		 * and we hold a reference to qdisc, so it is safe to release
+		 * rcu read lock.
+		 */
+		rcu_read_unlock();
+
 		/* 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);
+				err = -ENOENT;
+				goto errout_qdisc;
 			}
 		}
 
 		/* And the last stroke */
 		block = cops->tcf_block(*q, *cl, extack);
-		if (!block)
-			return ERR_PTR(-EINVAL);
+		if (!block) {
+			err = -EINVAL;
+			goto errout_qdisc;
+		}
 		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);
+			err = -EOPNOTSUPP;
+			goto errout_qdisc;
 		}
+
+		/* Always take reference to block in order to support execution
+		 * of rules update path of cls API without rtnl lock. Caller
+		 * must release block when it is finished using it. 'if' block
+		 * of this conditional obtain reference to block by calling
+		 * tcf_block_refcnt_get().
+		 */
+		refcount_inc(&block->refcnt);
 	}
 
 	return block;
+
+errout_rcu:
+	rcu_read_unlock();
+errout_qdisc:
+	if (*q)
+		qdisc_put(*q);
+	return ERR_PTR(err);
+}
+
+static void tcf_block_release(struct Qdisc *q, struct tcf_block *block)
+{
+	if (!IS_ERR_OR_NULL(block))
+		tcf_block_refcnt_put(block);
+
+	if (q)
+		qdisc_put(q);
 }
 
 struct tcf_block_owner_item {
@@ -664,21 +796,16 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 {
 	struct net *net = qdisc_net(q);
 	struct tcf_block *block = NULL;
-	bool created = false;
 	int err;
 
-	if (ei->block_index) {
+	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++;
-	}
+		block = tcf_block_refcnt_get(net, ei->block_index);
 
 	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)
@@ -708,14 +835,8 @@ err_block_offload_bind:
 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--;
-	}
+	tcf_block_refcnt_put(block);
 	return err;
 }
 EXPORT_SYMBOL(tcf_block_get_ext);
@@ -747,42 +868,12 @@ EXPORT_SYMBOL(tcf_block_get);
 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);
-	} else {
-		block->refcnt--;
-	}
+	__tcf_block_put(block, q, ei);
 }
 EXPORT_SYMBOL(tcf_block_put_ext);
 
@@ -1332,6 +1423,7 @@ replay:
 errout:
 	if (chain)
 		tcf_chain_put(chain);
+	tcf_block_release(q, block);
 	if (err == -EAGAIN)
 		/* Replay the request. */
 		goto replay;
@@ -1453,6 +1545,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 errout:
 	if (chain)
 		tcf_chain_put(chain);
+	tcf_block_release(q, block);
 	return err;
 }
 
@@ -1538,6 +1631,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 errout:
 	if (chain)
 		tcf_chain_put(chain);
+	tcf_block_release(q, block);
 	return err;
 }
 
@@ -1636,7 +1730,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		return err;
 
 	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
-		block = tcf_block_lookup(net, tcm->tcm_block_index);
+		block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
 		if (!block)
 			goto out;
 		/* If we work with block index, q is NULL and parent value
@@ -1695,6 +1789,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		}
 	}
 
+	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
+		tcf_block_refcnt_put(block);
 	cb->args[0] = index;
 
 out:
@@ -1854,7 +1950,8 @@ replay:
 	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;
+		err = -EINVAL;
+		goto errout_block;
 	}
 	chain = tcf_chain_lookup(block, chain_index);
 	if (n->nlmsg_type == RTM_NEWCHAIN) {
@@ -1866,23 +1963,27 @@ replay:
 				tcf_chain_hold(chain);
 			} else {
 				NL_SET_ERR_MSG(extack, "Filter chain already exists");
-				return -EEXIST;
+				err = -EEXIST;
+				goto errout_block;
 			}
 		} 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;
+				err = -ENOENT;
+				goto errout_block;
 			}
 			chain = tcf_chain_create(block, chain_index);
 			if (!chain) {
 				NL_SET_ERR_MSG(extack, "Failed to create filter chain");
-				return -ENOMEM;
+				err = -ENOMEM;
+				goto errout_block;
 			}
 		}
 	} else {
 		if (!chain || tcf_chain_held_by_acts_only(chain)) {
 			NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
-			return -EINVAL;
+			err = -EINVAL;
+			goto errout_block;
 		}
 		tcf_chain_hold(chain);
 	}
@@ -1926,6 +2027,8 @@ replay:
 
 errout:
 	tcf_chain_put(chain);
+errout_block:
+	tcf_block_release(q, block);
 	if (err == -EAGAIN)
 		/* Replay the request. */
 		goto replay;
@@ -1954,7 +2057,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 		return err;
 
 	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
-		block = tcf_block_lookup(net, tcm->tcm_block_index);
+		block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
 		if (!block)
 			goto out;
 		/* If we work with block index, q is NULL and parent value
@@ -2021,6 +2124,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 		index++;
 	}
 
+	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK)
+		tcf_block_refcnt_put(block);
 	cb->args[0] = index;
 
 out:
@@ -2213,6 +2318,7 @@ static __net_init int tcf_net_init(struct net *net)
 {
 	struct tcf_net *tn = net_generic(net, tcf_net_id);
 
+	spin_lock_init(&tn->idr_lock);
 	idr_init(&tn->idr);
 	return 0;
 }
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 411c40344b77..22e9799e5b69 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -314,6 +314,24 @@ out:
 	return q;
 }
 
+struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle)
+{
+	struct netdev_queue *nq;
+	struct Qdisc *q;
+
+	if (!handle)
+		return NULL;
+	q = qdisc_match_from_root(dev->qdisc, handle);
+	if (q)
+		goto out;
+
+	nq = dev_ingress_queue_rcu(dev);
+	if (nq)
+		q = qdisc_match_from_root(nq->qdisc_sleeping, handle);
+out:
+	return q;
+}
+
 static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
 {
 	unsigned long cl;
@@ -920,7 +938,7 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 		qdisc_notify(net, skb, n, clid, old, new);
 
 	if (old)
-		qdisc_destroy(old);
+		qdisc_put(old);
 }
 
 /* Graft qdisc "new" to class "classid" of qdisc "parent" or
@@ -973,7 +991,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 				qdisc_refcount_inc(new);
 
 			if (!ingress)
-				qdisc_destroy(old);
+				qdisc_put(old);
 		}
 
 skip:
@@ -1561,7 +1579,7 @@ graft:
 	err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack);
 	if (err) {
 		if (q)
-			qdisc_destroy(q);
+			qdisc_put(q);
 		return err;
 	}
 
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index cd49afca9617..d714d3747bcb 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -150,7 +150,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl)
 	pr_debug("atm_tc_put: destroying\n");
 	list_del_init(&flow->list);
 	pr_debug("atm_tc_put: qdisc %p\n", flow->q);
-	qdisc_destroy(flow->q);
+	qdisc_put(flow->q);
 	tcf_block_put(flow->block);
 	if (flow->sock) {
 		pr_debug("atm_tc_put: f_count %ld\n",
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index f42025d53cfe..4dc05409e3fb 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1418,7 +1418,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl)
 	WARN_ON(cl->filters);
 
 	tcf_block_put(cl->block);
-	qdisc_destroy(cl->q);
+	qdisc_put(cl->q);
 	qdisc_put_rtab(cl->R_tab);
 	gen_kill_estimator(&cl->rate_est);
 	if (cl != &q->link)
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index e26a24017faa..e689e11b6d0f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -379,7 +379,7 @@ static void cbs_destroy(struct Qdisc *sch)
 	cbs_disable_offload(dev, q);
 
 	if (q->qdisc)
-		qdisc_destroy(q->qdisc);
+		qdisc_put(q->qdisc);
 }
 
 static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index e0b0cf8a9939..cdebaed0f8cf 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -134,7 +134,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 					    tca[TCA_RATE]);
 		if (err) {
 			NL_SET_ERR_MSG(extack, "Failed to replace estimator");
-			qdisc_destroy(cl->qdisc);
+			qdisc_put(cl->qdisc);
 			kfree(cl);
 			return err;
 		}
@@ -153,7 +153,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl)
 {
 	gen_kill_estimator(&cl->rate_est);
-	qdisc_destroy(cl->qdisc);
+	qdisc_put(cl->qdisc);
 	kfree(cl);
 }
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 049714c57075..f6f480784bc6 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -412,7 +412,7 @@ static void dsmark_destroy(struct Qdisc *sch)
 	pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p);
 
 	tcf_block_put(p->block);
-	qdisc_destroy(p->q);
+	qdisc_put(p->q);
 	if (p->mv != p->embedded)
 		kfree(p->mv);
 }
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index 24893d3b5d22..3809c9bf8896 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -177,7 +177,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops,
 	if (q) {
 		err = fifo_set_limit(q, limit);
 		if (err < 0) {
-			qdisc_destroy(q);
+			qdisc_put(q);
 			q = NULL;
 		}
 	}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a64132a5db36..531fac1d2875 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -901,7 +901,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
 	if (!ops->init || ops->init(sch, NULL, extack) == 0)
 		return sch;
 
-	qdisc_destroy(sch);
+	qdisc_put(sch);
 	return NULL;
 }
 EXPORT_SYMBOL(qdisc_create_dflt);
@@ -941,15 +941,18 @@ void qdisc_free(struct Qdisc *qdisc)
 	kfree((char *) qdisc - qdisc->padded);
 }
 
-void qdisc_destroy(struct Qdisc *qdisc)
+void qdisc_free_cb(struct rcu_head *head)
+{
+	struct Qdisc *q = container_of(head, struct Qdisc, rcu);
+
+	qdisc_free(q);
+}
+
+static void qdisc_destroy(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops  *ops = qdisc->ops;
 	struct sk_buff *skb, *tmp;
 
-	if (qdisc->flags & TCQ_F_BUILTIN ||
-	    !refcount_dec_and_test(&qdisc->refcnt))
-		return;
-
 #ifdef CONFIG_NET_SCHED
 	qdisc_hash_del(qdisc);
 
@@ -974,9 +977,34 @@ void qdisc_destroy(struct Qdisc *qdisc)
 		kfree_skb_list(skb);
 	}
 
-	qdisc_free(qdisc);
+	call_rcu(&qdisc->rcu, qdisc_free_cb);
+}
+
+void qdisc_put(struct Qdisc *qdisc)
+{
+	if (qdisc->flags & TCQ_F_BUILTIN ||
+	    !refcount_dec_and_test(&qdisc->refcnt))
+		return;
+
+	qdisc_destroy(qdisc);
+}
+EXPORT_SYMBOL(qdisc_put);
+
+/* Version of qdisc_put() that is called with rtnl mutex unlocked.
+ * Intended to be used as optimization, this function only takes rtnl lock if
+ * qdisc reference counter reached zero.
+ */
+
+void qdisc_put_unlocked(struct Qdisc *qdisc)
+{
+	if (qdisc->flags & TCQ_F_BUILTIN ||
+	    !refcount_dec_and_rtnl_lock(&qdisc->refcnt))
+		return;
+
+	qdisc_destroy(qdisc);
+	rtnl_unlock();
 }
-EXPORT_SYMBOL(qdisc_destroy);
+EXPORT_SYMBOL(qdisc_put_unlocked);
 
 /* Attach toplevel qdisc to device queue. */
 struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
@@ -1270,7 +1298,7 @@ static void shutdown_scheduler_queue(struct net_device *dev,
 		rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
 		dev_queue->qdisc_sleeping = qdisc_default;
 
-		qdisc_destroy(qdisc);
+		qdisc_put(qdisc);
 	}
 }
 
@@ -1279,7 +1307,7 @@ void dev_shutdown(struct net_device *dev)
 	netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
 	if (dev_ingress_queue(dev))
 		shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
-	qdisc_destroy(dev->qdisc);
+	qdisc_put(dev->qdisc);
 	dev->qdisc = &noop_qdisc;
 
 	WARN_ON(timer_pending(&dev->watchdog_timer));
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3278a76f6861..b18ec1f6de60 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1092,7 +1092,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl)
 	struct hfsc_sched *q = qdisc_priv(sch);
 
 	tcf_block_put(cl->block);
-	qdisc_destroy(cl->qdisc);
+	qdisc_put(cl->qdisc);
 	gen_kill_estimator(&cl->rate_est);
 	if (cl != &q->root)
 		kfree(cl);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 18ac2d6ca294..58b449490757 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1208,7 +1208,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
 {
 	if (!cl->level) {
 		WARN_ON(!cl->leaf.q);
-		qdisc_destroy(cl->leaf.q);
+		qdisc_put(cl->leaf.q);
 	}
 	gen_kill_estimator(&cl->rate_est);
 	tcf_block_put(cl->block);
@@ -1409,7 +1409,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			/* turn parent into inner node */
 			qdisc_reset(parent->leaf.q);
 			qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog);
-			qdisc_destroy(parent->leaf.q);
+			qdisc_put(parent->leaf.q);
 			if (parent->prio_activity)
 				htb_deactivate(q, parent);
 
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index d6b8ae4ed7a3..f20f3a0f8424 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -65,7 +65,7 @@ static void mq_destroy(struct Qdisc *sch)
 	if (!priv->qdiscs)
 		return;
 	for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
-		qdisc_destroy(priv->qdiscs[ntx]);
+		qdisc_put(priv->qdiscs[ntx]);
 	kfree(priv->qdiscs);
 }
 
@@ -119,7 +119,7 @@ static void mq_attach(struct Qdisc *sch)
 		qdisc = priv->qdiscs[ntx];
 		old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
 		if (old)
-			qdisc_destroy(old);
+			qdisc_put(old);
 #ifdef CONFIG_NET_SCHED
 		if (ntx < dev->real_num_tx_queues)
 			qdisc_hash_add(qdisc, false);
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 0e9d761cdd80..d364e63c396d 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -40,7 +40,7 @@ static void mqprio_destroy(struct Qdisc *sch)
 		for (ntx = 0;
 		     ntx < dev->num_tx_queues && priv->qdiscs[ntx];
 		     ntx++)
-			qdisc_destroy(priv->qdiscs[ntx]);
+			qdisc_put(priv->qdiscs[ntx]);
 		kfree(priv->qdiscs);
 	}
 
@@ -300,7 +300,7 @@ static void mqprio_attach(struct Qdisc *sch)
 		qdisc = priv->qdiscs[ntx];
 		old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
 		if (old)
-			qdisc_destroy(old);
+			qdisc_put(old);
 		if (ntx < dev->real_num_tx_queues)
 			qdisc_hash_add(qdisc, false);
 	}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 1da7ea8de0ad..7410ce4d0321 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -175,7 +175,7 @@ multiq_destroy(struct Qdisc *sch)
 
 	tcf_block_put(q->block);
 	for (band = 0; band < q->bands; band++)
-		qdisc_destroy(q->queues[band]);
+		qdisc_put(q->queues[band]);
 
 	kfree(q->queues);
 }
@@ -204,7 +204,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
 			q->queues[i] = &noop_qdisc;
 			qdisc_tree_reduce_backlog(child, child->q.qlen,
 						  child->qstats.backlog);
-			qdisc_destroy(child);
+			qdisc_put(child);
 		}
 	}
 
@@ -228,7 +228,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
 					qdisc_tree_reduce_backlog(old,
 								  old->q.qlen,
 								  old->qstats.backlog);
-					qdisc_destroy(old);
+					qdisc_put(old);
 				}
 				sch_tree_unlock(sch);
 			}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 506e1960ed7f..57b3ad9394ad 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1022,7 +1022,7 @@ static void netem_destroy(struct Qdisc *sch)
 
 	qdisc_watchdog_cancel(&q->watchdog);
 	if (q->qdisc)
-		qdisc_destroy(q->qdisc);
+		qdisc_put(q->qdisc);
 	dist_free(q->delay_dist);
 	dist_free(q->slot_dist);
 }
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 222e53d3d27a..f8af98621179 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -175,7 +175,7 @@ prio_destroy(struct Qdisc *sch)
 	tcf_block_put(q->block);
 	prio_offload(sch, NULL);
 	for (prio = 0; prio < q->bands; prio++)
-		qdisc_destroy(q->queues[prio]);
+		qdisc_put(q->queues[prio]);
 }
 
 static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
@@ -205,7 +205,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
 					      extack);
 		if (!queues[i]) {
 			while (i > oldbands)
-				qdisc_destroy(queues[--i]);
+				qdisc_put(queues[--i]);
 			return -ENOMEM;
 		}
 	}
@@ -220,7 +220,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
 
 		qdisc_tree_reduce_backlog(child, child->q.qlen,
 					  child->qstats.backlog);
-		qdisc_destroy(child);
+		qdisc_put(child);
 	}
 
 	for (i = oldbands; i < q->bands; i++) {
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index bb1a9c11fc54..dc37c4ead439 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -526,7 +526,7 @@ set_change_agg:
 	return 0;
 
 destroy_class:
-	qdisc_destroy(cl->qdisc);
+	qdisc_put(cl->qdisc);
 	kfree(cl);
 	return err;
 }
@@ -537,7 +537,7 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl)
 
 	qfq_rm_from_agg(q, cl);
 	gen_kill_estimator(&cl->rate_est);
-	qdisc_destroy(cl->qdisc);
+	qdisc_put(cl->qdisc);
 	kfree(cl);
 }
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 56c181c3feeb..3ce6c0a2c493 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -181,7 +181,7 @@ static void red_destroy(struct Qdisc *sch)
 
 	del_timer_sync(&q->adapt_timer);
 	red_offload(sch, false);
-	qdisc_destroy(q->qdisc);
+	qdisc_put(q->qdisc);
 }
 
 static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
@@ -233,7 +233,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 	if (child) {
 		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
 					  q->qdisc->qstats.backlog);
-		qdisc_destroy(q->qdisc);
+		qdisc_put(q->qdisc);
 		q->qdisc = child;
 	}
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 7cbdad8419b7..bab506b01a32 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -469,7 +469,7 @@ static void sfb_destroy(struct Qdisc *sch)
 	struct sfb_sched_data *q = qdisc_priv(sch);
 
 	tcf_block_put(q->block);
-	qdisc_destroy(q->qdisc);
+	qdisc_put(q->qdisc);
 }
 
 static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = {
@@ -523,7 +523,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt,
 
 	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
 				  q->qdisc->qstats.backlog);
-	qdisc_destroy(q->qdisc);
+	qdisc_put(q->qdisc);
 	q->qdisc = child;
 
 	q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval);
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a4530e85bd02..942dcca09cf2 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -392,7 +392,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	if (child) {
 		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
 					  q->qdisc->qstats.backlog);
-		qdisc_destroy(q->qdisc);
+		qdisc_put(q->qdisc);
 		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
@@ -438,7 +438,7 @@ static void tbf_destroy(struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
 	qdisc_watchdog_cancel(&q->watchdog);
-	qdisc_destroy(q->qdisc);
+	qdisc_put(q->qdisc);
 }
 
 static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)